pith. sign in

q-fin

Quantitative Finance

Top Pith
5
q-fin.MF 2026-06-29

Lean 4 verifies arbitrage-free markets admit martingale measures

by Raphael Coelho

The Fundamental Theorem of Asset Pricing, Formalized in Lean 4

Explicit minimization of a convex potential replaces Hahn-Banach in the multi-asset one-period case.

Figure from the paper full image
abstract click to expand
The Fundamental Theorem of Asset Pricing states that a market is free of arbitrage exactly when it admits an equivalent martingale measure. We formalize it in Lean 4 over Mathlib in three settings: a finite-state market over a finite horizon (Harrison-Pliska), a one-period market on an arbitrary probability space with a single scalar return (Follmer-Schied), and a one-period market with finitely many assets. The finite case is the geometry of a separating hyperplane; the scalar one-period case is an elementary change of measure. In the $d$-asset case the equivalent martingale measure is constructed explicitly, as the minimiser of the smooth convex potential $\mathbb{E}[\log(1+e^{\langle\theta,Y\rangle})]$: absence of arbitrage is precisely coercivity of the potential, its first-order condition is the martingale property, and the minimiser's logistic weight is the density of the measure. The construction uses no Hahn-Banach theorem, no $L^0$-closedness argument, no measurable selection, and no non-redundancy hypothesis. To our knowledge this is the first machine-checked Fundamental Theorem of Asset Pricing in any proof assistant. The boundary is explicit: the general multi-period Dalang-Morton-Willinger theorem lies outside the development. Every theorem is sorry-free, each headline result's axioms are pinned to Mathlib's classical defaults by a build-enforced gate, and the whole is reproducible from a pinned toolchain.
0
Top Pith
2
cs.CY 2026-05-05

AI markets will pay premiums for verified human presence

by Erin McGurk, David Khachaturov

Human-Provenance Verification should be Treated as Labor Infrastructure in AI-Saturated Markets

As synthetic substitutes erode middle-tier knowledge work, governance must treat provenance verification as labor infrastructure to support

Figure from the paper full image
abstract click to expand
We argue that AI-saturated markets are likely to create Veblen-good premiums, which we term human-provenance premiums, for verified human presence, and hence AI governance should treat human-provenance verification as labor infrastructure. Generative and agentic AI systems lower the cost of many standardized cognitive, creative, and coordination tasks, weakening the scarcity premiums that have supported much middle-tier knowledge work. We argue that this pressure may produce an asymmetric barbell-shaped structure of value capture in advanced economies: high-volume synthetic production controlled by owners of AI infrastructure at one pole, and scarce, high-status human labor valued for verified human presence at the other. We advance three claims. First, AI compresses the value of standardized middle-tier labor by making good-enough synthetic substitutes scalable at low marginal cost, hollowing out the middle of the skill distribution currently categorized by knowledge work. Second, this compression reallocates demand for human labor toward work valued for its visible human character. We term this performative humanity and distinguish three forms of labor: relational presence, aesthetic provenance, and accountability. Third, as these premiums depend on credible verification, AI governance should treat human-provenance systems as labor infrastructure rather than as luxury authenticity labels. To evaluate hybrid human-AI work, we propose constitutive human presence as the relevant standard: human labor retains premium value when human judgment, attention, accountability, authorship, or relational participation is not incidental to the output but constitutive of what is being purchased.
0
Top Pith
1
cs.MA 2026-04-30

AI buyer agents leak willingness to pay from dialogue

by Soogand Alavi, Salar Nozari

When Agents Shop for You: Role Coherence in AI-Mediated Markets

Seller inference recovers budgets nearly one-for-one from natural-language profiles, and confidentiality instructions do not stop it.

Figure from the paper full image
abstract click to expand
Consumers are increasingly delegating purchase decisions to AI agents, providing natural-language descriptions of their preferences and identity. We argue that these representations constitute an information channel, role coherence, through which sellers can infer willingness to pay without explicit disclosure by the buyer agent, leading to preference leakage. In an experiment where a language-model buyer agent shops on behalf of a verbal consumer profile, we show that seller-side inference from dialogue alone recovers willingness to pay nearly one-for-one. Comparing this setting to a numeric-budget condition with confidentiality instructions cleanly isolates role coherence as distinct from instruction-following failure. Because this leakage arises from delegation itself, it cannot be mitigated at the prompt level. Instead, we propose architectural interventions that trade off personalization against preference privacy.
1 0
0
q-fin.GN 2026-07-03

Cap-axis curve checks whether factors price cap-rank subspace

by Useong Shin

A Cap-Axis Integral Diagnostic of Factor Models

Lifting pricing errors along capitalization axis flags subspace violations even when Sharpe frontier improves

Figure from the paper full image
abstract click to expand
I propose a cap-axis integral diagnostic for factor-model evaluation. Low-dimensional factor models can improve the maximum-Sharpe frontier while leaving zero-alpha violations on economically fixed subspaces. The diagnostic studies one such subspace by lifting pricing errors into a bridge-alpha curve along the market-capitalization rank axis. Under an aggregate-market gate, a zero curve is equivalent to pricing the market's internal cap-rank subspace. In 1967-2024 CRSP data, q5's daily negative bridge attenuates under lead-lag correction, while Fama-French and Carhart bridges are more visible monthly. Across 154 factors, the cap-axis norm is distinct from Sharpe gain and size exposure.
0
0
q-fin.MF 2026-07-03

MACD signals emerge as optimal estimators of latent asset drift

by Dannin J. Eccles, Roger Lee

Portfolio Optimization under Fast and Slow Latent Mean-Reverting and Momentum Drift

In two-scale latent factor models the filtered mean-reversion level reduces to fast-slow EMA difference plus Volterra term.

abstract click to expand
We consider a class of partial-information portfolio optimization problems in which the drift of a risky asset is driven by two latent stochastic factors evolving at distinct time scales. We show that the filtered estimate of the latent mean-reversion level is driven by the difference between fast and slow exponential moving average (EMA)-type processes of the trailing price history, yielding a Moving Average Convergence Divergence (MACD)-type signal, along with a deterministic Volterra correction. Under logarithmic, power, and exponential utility, we derive candidate optimal strategies in explicit feedback form and establish admissibility and verification results. In particular, the results provide a mathematical foundation for the endogenous emergence of MACD-type trading signals as estimators of latent drift information contained in observed price paths.
0
0
econ.GN 2026-07-03

Four components turned negative in Japan's 1996-2014 wage stagnation

by Ken Yamada

Decomposing Wage Stagnation: Employment Reallocation, Wage Structure,and Demographics

Within-job growth was positive over decades but demographics, reallocation, and relative wage shifts offset it after the mid-1990s.

Figure from the paper full image
abstract click to expand
Average wages in Japan rose until the mid-1990s but stagnated thereafter. This paper studies Japan's long-run wage stagnation by decomposing changes in average log real hourly wages from 1980 to 2024 into four components: demographic change across worker types, changes in relative employment shares across job types, changes in relative wages across job types, and wage growth within job types. The framework combines a shift-share decomposition across worker types with an extension of the Olley-Pakes decomposition that separates employment reallocation from changes in relative wages across job types. Wage growth within job types contributes positively over the full sample period, but demographic change and employment reallocation partly offset it. Between 1996 and 2014, all four components are negative. The negative contribution from employment reallocation is not limited to the expansion of part-time employment, but reflects broader shifts across job types defined by employment type, establishment size, and industry.
0
0
q-fin.TR 2026-07-03

Trend profits collapsed on small-tick futures after 2008

by Jutta G. Kurth, Zoltan Eisler +2 more

Is Trend Still Your Friend?: A Microstructural Account of the Demise of Short-Term Trend-Following

The split by volatility-normalised tick size shows HFT liquidity withdrawal broke the impact loop that once sustained short-term trends.

Figure from the paper full image
abstract click to expand
Systematic trend following has, on average, been profitable for at least two centuries; yet since approximately 2009, short-term trends have ceased to deliver reliable returns. Using a cross-section of roughly 100 liquid futures contracts spanning 1995-2025, together with an industry-representative CTA proxy, we document the break and characterise its dependence on signal speed and asset class. We evaluate four candidate explanations - capacity constraints, market electronification, a regime change in CTA-versus-order-flow interactions, and a microstructural mechanism - and find that the first three fail on grounds of timing, magnitude, or cross-sectional heterogeneity. Our central empirical finding is that the cross-sectional variable distinguishing degraded from surviving trends is the volatility-normalised tick size: post-2008 trend PnL has collapsed on small-tick contracts across all signal horizons, while remaining essentially intact on large-tick ones. Neither asset class nor liquidity replicates this dichotomy. We interpret this result through a self-fulfilling feedback loop that, in our view, lies at the heart of the trend anomaly itself: trend signals trigger directional trades, whose market impact reinforces the very price moves that generated the signal. Both the profitability and the persistence of trend are sustained by this impact channel, which requires that trend followers can execute aggressively at reasonable cost. We argue that the post-crisis transition to HFT-dominated market making, whose liquidity-withdrawal behaviour in front of predictable directional flow has sharply contrasting consequences for sparse (small-tick) and dense (large-tick) limit order books, has broken this loop on small-tick contracts. On large-tick contracts, residual depth remains sufficient, and the loop continues to operate.
0
0
econ.EM 2026-07-02

Low order flow creates illiquidity premium via price impact

by Irene Aldridge

Liquidity Premium and Investment Horizons

Daily estimates of Kyle's lambda from equity order flow forecast returns and resolve Constantinides puzzle through temporary price depressio

Figure from the paper full image
abstract click to expand
We estimate Kyle's (1985) price-impact coefficient $\lambda$ directly from daily equity order flow and test its ability to forecast the cross-section of subsequent stock returns. Using CRSP data from 2020 to 2025, we construct firm-month measures of signed order flow and two estimators of $\hat\lambda_{it}$: a within-month price-impact regression and an Amihud-style ratio. Signed order flow strongly predicts contemporaneous and one-month-ahead returns, while volume volatility predicts lower subsequent returns, consistent with widening price impact degrading price discovery. Fama-MacBeth regressions confirm that our order-flow signal carries significant cross-sectional return information after Newey--West adjustment. Theoretically, we resolve the liquidity premium puzzle of Constantinides (1986) through an adverse-selection mechanism: low order flow widens $\lambda$ and depresses prices today; subsequent normalization restores prices, generating the illiquidity premium without risk-based compensation.
0
0
q-fin.TR 2026-07-02

Heavy liquidity tails make large trades less news-like

by Umut Çetin, Mingwei Lin +1 more

When large trades are not news: Liquidity tail risk and price discovery

Student-t uninformed demand keeps imbalances ambiguous, flattening impact and slowing price discovery from order flow.

abstract click to expand
When is a large trade news, and when is it a liquidity shock? We study this question in a sequential competitive limit order book with asymmetric information. In our model, liquidity suppliers observe aggregate order flow but not its decomposition into informed demand and uninformed liquidity demand. We model uninformed order flow with Student-$t$ tails, interpreted as a reduced form for rare liquidity regimes. The tail index of liquidity demand determines how informative large trades are. With thin-tailed noise, large order imbalances are quickly interpreted as private information. With heavy-tailed liquidity demand, the same imbalances remain plausibly liquidity-driven. This liquidity-tail ambiguity flattens and concavifies price impact, slows learning from order flow, and delays the decline of adverse-selection premia. We characterize equilibrium through a fixed-point equation for the marginal-cost schedule. Heavy-tailed liquidity demand changes the mathematics of equilibrium: the Gaussian monotonicity and compactness arguments fail because remote liquidity states remain pricing-relevant at polynomial order. We construct fixed points on a tail-controlled compact class and study learning and large-order asymptotics along selected monotone branches. Repeated order flow reveals the fundamental value under stable information-rate conditions, but heavier liquidity tails slow finite-horizon price discovery. Large-order impact obeys regular-variation asymptotics whose exponents depend on the liquidity-tail index, informed competition, and posterior beliefs. The model identifies liquidity tail risk as a state variable for market impact, spread resilience, and the informativeness of large trades.
0
0
econ.GN 2026-07-02

AI productivity lifts builder wages above GDP growth

by Matthew O. Jackson, Zafer Kanik

The Economic Benefits and Costs of AI and Policies to Mitigate AI's Impact on Inequality

Substituted workers see absolute and relative declines, with policy responses varying by whether AI production is competitive or monopolisti

Figure from the paper full image
abstract click to expand
We examine the economic impact of increasingly productive AI and policies that spread its benefits across the economy. Improvements in AI productivity trigger labor reallocation and changes in absolute and relative wages for different types of labor. Wages of labor that is essential for building AI increase faster than overall GDP. Wages of labor that is substituted for by AI decrease in both absolute and relative terms. Wages of labor that is used only in final goods production and is not displaced by AI increase in line with overall GDP. We contrast the impact of productivity gains depending on whether AI production is competitive or monopolistic. Monopoly production of AI restricts its deployment, slowing the transition and impact of AI. Optimal tax and regulatory policies that achieve Pareto-improvements differ depending on whether there is competition in AI production.
0
0
econ.GN 2026-07-02

Scarce import headroom raises German plant withholding odds 15% per GW

by Alice Lixuan Xu, Clemens Stiewe

Competitive effects of transmission constraints in the German electricity market

When transmission capacity is nearly exhausted, plants are more likely to deviate from competitive dispatch in ways suggesting strategic beh

Figure from the paper full image
abstract click to expand
This paper estimates the effect of cross-border transmission constraints on suspected market power abuse in the German wholesale electricity market. Using a 2SRI instrumental variables approach, we study suspected strategic behavior by German gas- and coal-fired power plants in 2022-2024. Cross-border transmission constraints are measured using the maximum and minimum bounds of zonal net position, while suspected market power abuse is measured as the upward or downward deviation of observed dispatch from a modeled competitive benchmark. We find that transmission constraints significantly elevate the likelihood of suspected market power abuse. When headroom for further imports is already scarce, reducing import headroom by one Gigawatt (GW) increases the odds of suspected capacity withholding by 15%. Similarly, reducing export headroom by one GW when it is scarce increases the odds of suspected capacity push-in, a strategy to depress prices, by 16%. These results provide empirical support for interconnection expansion as an instrument to mitigate market power.
0
0
q-fin.MF 2026-07-02

Puts and trend following split protection across crash and drawdown regimes

by Miquel Noguer i Alonso, Ali Al Fallouji

Tail Risk Management with Puts and Trend Following: A CVaR Framework for Crashes and Drawdowns

A CVaR model shows immediate jump repricing from options versus lagged but sustained defense from trend signals, supporting hybrid mandates.

Figure from the paper full image
abstract click to expand
Tail-risk management is not only an instrument-selection problem. It is an allocation problem across loss mechanisms: abrupt crash states, volatility repricing, and persistent drawdowns require different forms of protection. This paper develops a continuous-time CVaR framework that places two common protection sleeves -- long out-of-the-money put options and systematic trend-following overlays -- inside one coherent tail-risk mandate. The option sleeve is modeled as a marked-to-market traded asset, so premium drag, diffusion exposure, and jump repricing enter through its physical return process rather than through inconsistent terminal-payoff accounting. The resulting Markov state contains wealth, spot, stochastic variance, and an exponentially weighted log-return signal, and we derive the associated Hamilton--Jacobi--Bellman equation in viscosity form. The main analytical separation is temporal: convex insurance reprices immediately on jump impact, whereas trend following is late on the first shock because its signal must cross zero, but becomes increasingly defensive during persistent drawdowns without requiring fresh option premium. We then give sufficient and local conditions for an interior hybrid allocation, derive a CVaR policy-gradient identity, and introduce a four-axis diagnostic layer separating conditional convexity, tail-event reliability, non-stress carry, and drawdown persistence. Stylized Monte Carlo experiments illustrate the mechanism: fixed equal-weight hybrids and grid-optimized hybrids reduce terminal CVaR relative to either pure sleeve in the reported regimes, while the exact weight location remains calibration-dependent. The contribution is a transparent risk-management framework for deciding how much convex crash protection and how much signal-driven drawdown protection a mandate should hold.
0
0
q-fin.CP 2026-07-02

Shapley values match financial expert reasoning in language model explanations

by Dangxing Chen, Pengzhan Guo

Shapley in Context: Explaining Financial Language with Domain Expertise

Attributions align with domain knowledge on financial text and reveal model behavior for regulatory use.

Figure from the paper full image
abstract click to expand
In recent years, large language models have achieved remarkable success and have seen growing adoption in financial applications. At the same time, explainability remains critical in finance, a domain characterized by high stakes and strict regulatory requirements. Although numerous methods have been proposed to explain black box machine learning models, the majority of these approaches are designed for general purpose tasks and do not incorporate domain specific knowledge. In this work, we study the explainability of financial textual data modeled by large language models through the lens of the Shapley value. Specifically, we investigate whether Shapley based attributions align with established financial domain knowledge. Through rigorous theoretical analysis and extensive empirical evaluations, we demonstrate that Shapley values can yield explanations that are consistent with financial reasoning and can offer meaningful insights into the model's behavior in text based financial applications.
0
0
econ.GN 2026-07-02

AI chats absorb routine politics and turn expressive only after major events

by Ziwen Zu

Talking Politics with Artificial Intelligence

4.3 million conversations show 3.9% political content that spikes in stance and emotion after the 2024 election result among U.S. users.

Figure from the paper full image
abstract click to expand
Large language models (LLMs), a prominent form of artificial intelligence (AI), are becoming everyday interfaces for political questions, but most exchanges are dyadic rather than audiencefacing. This paper asks whether AI conversation functions as a new arena for political expression or as a conversational intermediary for routine political demand. Using 4.30 million humanAI conversations from three large public datasets, we apply two validated classifiers to user messages, identifying political content, use case, and expressed ideology. Political content appears in 3.9% of conversations, varies sharply by platform publicness and conversation depth, and is mostly practical: users ask for information, draft text, and process documents far more often than they state opinions. A regression-discontinuity-in-time design around the 2024 U.S. presidential result call shows that the call changed the expressive subset: among U.S. users, stance-taking, affective language, and ideological extremity rose; comparable conversations elsewhere did not. AI conversation is less a public square than a conversational political intermediary, absorbing routine demand and becoming expressive when major events make political stakes explicit.
0
0
econ.GN 2026-07-02

Optimistic inflow bias lowers reservoirs and raises hydro costs

by Arthur Brigatto, Alexandre Street +1 more

How optimistic inflow forecasts distort dispatch, prices, and contracts in hydro-dominated power systems: evidence from Brazil

Biased forecasts reduce water values, increase early discharge, and produce sharper price peaks plus higher operating costs in Brazil's syst

Figure from the paper full image
abstract click to expand
Centralized hydrothermal planning models determine generation schedules and electricity spot prices based on inflow forecasts in audited-cost power systems, such as those prevalent in Latin America, and provide operational benchmarks and decision support in hydro-dominated competitive electricity markets. Consequently, biased forecasts can propagate directly into both operational decisions and market outcomes. This paper studies how persistent optimistic inflow-forecast bias propagates through the Brazilian hydrothermal power system and market. For a stylized hydrothermal model, we show analytically that optimistic bias weakly reduces water values and weakly increases first-stage hydro discharge relative to the unbiased optimum, thereby lowering reservoir storage and postponing thermal commitment. Using official Brazilian planning and operational data, we provide empirical evidence consistent with this mechanism. We then conduct a controlled SDDP experiment to compare policies trained under biased and bias-corrected inflow-forecast processes, evaluating both under the same bias-corrected inflow scenarios. The policy trained under biased forecasts produces lower reservoir levels, delayed dry-season thermal dispatch, sharper spot-price peaks, higher reliability risk, and higher expected operating costs. Finally, we show that these distortions increase the price-quantity risk for hydropower producers and reduce their willingness to contract. The results indicate that inflow-forecast bias is not merely a statistical forecasting problem, but can be a source of operational inefficiency, reliability risk, and distorted market incentives in hydro-dominated power systems. We argue that the insights and policy implications drawn in this paper may be relevant beyond Brazil to other hydro-dominated systems and electricity markets that are increasingly reliant on energy storage.
0
0
q-fin.ST 2026-07-02

AI timing beats rules in futures

by Austin Pollok, Kevin Robik

End-to-End Parametric Portfolio Policies for Cross-Asset Futures Timing: When Do AI Models Beat Simple Rules?

On liquid CME contracts, learned policies outperform equal weighting and momentum after transaction costs due to reduced trading.

Figure from the paper full image
abstract click to expand
Timing-based tilts across asset classes can drive much of the risk and return of a diversified cross-asset portfolio. The standard approach forecasts returns and then optimizes weights. We instead study an end-to-end AI-based policy that maps market states directly to portfolio weights, and we then ask when this one-step modeling approach outperforms simple rules-based strategies. We train these policies on the sixteen most liquid CME futures, where an edge is unlikely to be due to illiquidity, using a differentiable Sharpe ratio loss function, and we benchmark them against equal weighting, risk parity, and time-series momentum. The learned policies rank above the rules on the pooled cross-asset portfolio and in several sub-asset classes, but not uniformly. In gross terms, an LSTM and a transformer-based architecture perform comparably out-of-sample, but diverge when we consider transaction costs. The transformer generates the stronger learned policy, trades far less than the LSTM, and matches or exceeds equal weighting through moderate cost.
0
0
econ.GN 2026-07-02

Warmer nights increase farm wage labor shares in rural India

by Vedarshi Shastry

Night and Day: Diurnal Warming and Structural Transformation in India

Census analysis 1981-2011 finds nights shift workers into paid agricultural roles but days move them to seasonal work, cutting output in bot

abstract click to expand
This paper finds diverging partial effects of diurnal warming (higher nighttime and daytime temperatures) on agricultural wage-labour shares from decadal Indian Censuses (1981-2011). Though both margins contract grain output and cultivated area, only higher maxima raise harvest prices locally, consistent with a model where warmer nights shock land but warmer days shock land and labour productivity. Warming nights shift seasonal workers and self-cultivators into agricultural labour; warming days push labour to the seasonal margin. Long differences show the labour divergence is rural. In towns, both margins depress non-agricultural worker shares.
0
0
q-fin.GN 2026-07-01

Blockchain tools let AI agents settle payments without losing accountability

by Hui Gong

Agent-to-Agent Finance: Blockchain Payments and Trust Infrastructure for Autonomous AI Agents

Agent-to-agent finance uses registries and verifiable settlement to handle machine-initiated transactions

Figure from the paper full image
abstract click to expand
Autonomous AI agents are beginning to occupy a position between analytical tools and transacting counterparties. They can interpret goals, call external tools, negotiate with other agents, access data and computation, and in some settings initiate payments or blockchain transactions. This development creates a distinct problem for financial markets: if software agents can act economically, market participants need infrastructure for identity, authorisation, payment, verification, reputation and accountability. This article develops the concept of agent-to-agent finance as the layer of machine-mediated financial interaction in which autonomous agents discover counterparties, purchase services, express transaction intent, execute payments and generate auditable evidence. The argument is not that blockchain is a universal substrate for finance, but that programmable settlement, smart wallets, decentralised registries and verifiable computation can address specific coordination frictions created by autonomous agents. Drawing on recent work on blockchain A2A payments, ERC-8004 agent registries, provenance-based wallets, deterministic inference, DeFi intent mining, and official evidence on AI adoption in financial services, the article situates agent-to-agent finance as an emerging form of financial market infrastructure. It argues that the decisive design question is bounded autonomy: how to let agents transact without making markets more opaque, fragile or unaccountable.
0
0
econ.GN 2026-07-01

Competition cuts dealer contract mistakes but leaves some

by David Huffman, Lamar Pierce +2 more

Competition and Anomalies Redux: Evidence from U.S. Auto Dealers

U.S. auto dealers choose wrong bonus contracts 20 percent of the time; rivalry lowers the rate mainly through changes inside existing dealer

Figure from the paper full image
abstract click to expand
We examine a choice between bonus contracts offered to dealers of a U.S. auto manufacturer. In our data, dealers select the non-profit-maximizing option in 20 percent of observations, costing the mistaken dealers $18,453 per year on average. We examine how the propensity to make this mistake varies with competition, identified both cross-sectionally and within dealers over time. Both analyses show that greater competition substantially lowers the rate of mistakes. However, even in the most competitive markets, consequential mistakes persist. Our results suggest that competition disciplines mainly through within-dealer changes in behavior rather than entry and exit.
0
0
q-fin.TR 2026-07-01

Manipulators extract wealth from short-horizon prediction contracts

by David Dai, Ruizhe Jia +1 more

Settlement Manipulation in Prediction Markets

Five-minute Bitcoin markets show settlement spikes and reversals while fifteen-minute versions do not, confirming the model's horizon remedy

abstract click to expand
Prediction markets increasingly list contracts settling on an asset price that holders can move by trading the underlying. We build a model showing that such contracts transfer wealth from prediction-market liquidity traders to manipulators and harm price discovery in the underlying, even as it becomes more liquid. After the launch of Polymarket's five-minute Bitcoin contract, settlement-time spot order flow spikes, causing large price reversals after settlement. Manipulators capture a large amount of profit, mostly from retail. Manipulation is largely absent in the fifteen-minute contracts: lengthening the contract horizon removes it, providing the market-design remedy our model and evidence support.
0
0
q-fin.ST 2026-07-01

Minimum eigenvalue gradient detects most VIX rogue peaks

by Rosie Hayward, Orla Lennon +1 more

Real-time identification of the onset of financial rogue waves

Kerr-nonlinear Schrödinger model on volatility indices flags 7 of 8 major spikes in real-time tests across VIX, VXO and VSTOXX.

Figure from the paper full image
abstract click to expand
Extreme events in financial systems, often captured by indicators such as volatility, remain difficult to identify close to their onset. Volatility shares many statistical properties with other natural, complex systems which experience extreme events, which we explore in this manuscript. We extend the analogy between rogue waves in optical and hydrodynamical systems to financial volatility by identifying rogue-wave-like peaks with similar statistical properties. We use a Schr\"odinger equation where the potential follows the shape of a Kerr nonlinearity to examine the properties of financial volatility indices within a moving time window. We see evidence of Anderson localisation as a rogue peak approaches in the VIX, and show that the numerical gradient of the system's minimum eigenvalue reliably spikes at the onset of an extreme event. We adapt our methodology to simulate the real-time arrival of data, and show that all but one of the VIX's major peaks can be detected given a reasonable amount of history. We then perform two out-of-sample tests, one for the VXO index, and one for the VSTOXX index, and successfully replicate our initial results, identifying all but one major peak (87.5% or 7/8) in both cases. This method of analysis shows considerable promise as a tool for identifying potential financial crises, aiding in their mitigation.
0
0
q-fin.GN 2026-07-01

Index membership widens greenwashing gap under some ESG ratings

by Praveen Kumar Ashok Kumar, Rafa{l} Sieradzki

Same Firms, Different Verdicts: ESG Rating Choice and the Measurement of Greenwashing

For 200 European firms, flagship status predicts larger disclosure-performance gaps with CDP scores but not LSEG, showing rating choice matt

Figure from the paper full image
abstract click to expand
This paper investigates the Aggregate Confusion hypothesis (Berg, Kolbel, and Rigobon, 2022) at the firm level by measuring the Disclosure-Performance Gap (DPG), the standardised divergence between a firm's voluntary environmental disclosure ("Talk") and its realised emissions performance ("Walk"). The sample comprises 200 large European firms from the Energy, Materials, Industrials, and Utilities sectors of the STOXX Europe 600 in fiscal year 2023, the final cross-section of the voluntary reporting era before the Corporate Sustainability Reporting Directive. The model is selected through a six-stage process, candidate assembly, correlation screening, VIF based multicollinearity filtering, stepwise forward search under the corrected Akaike Information Criterion, Cook's distance screening, and HC3 re-estimation across 421 candidate specifications, estimated by ordinary least squares with HC3 robust standard errors on the full sample. Flagship index membership is the strongest predictor of a wider gap ($\beta$ = +0.78, p < 0.01), consistent with institutional ceremonial conformity. TCFD endorsement is also positive ($\beta$ = +0.86, p < 0.05) but identified off a small group of non-supporting firms, so it is read as directional, not a precise magnitude. Renewable energy use ($\beta$ = -0.31, p < 0.01) and environmental capital expenditure ($\beta$ = -0.22, p < 0.05) significantly narrow the gap, consistent with signalling theory, while governance and monitoring variables carry no explanatory power. Results are robust to influence trimming, rank-based recoding of the disclosure score, and removal of the TCFD variable. Replacing the CDP Climate Score with the LSEG Environmental Pillar Score eliminates the index-membership effect while the renewable-energy effect survives, showing that detected greenwashing is conditional on the rating lens applied.
0
0
q-fin.TR 2026-07-01

Signature method reduces execution to quadratic program

by Gianmarco Morbelli, Sven Karbach +1 more

Signature-Based Optimal Execution for Statistical Arbitrage with Path-Dependent Trading Signals

Alpha and trading speed on the same truncated signature basis yield policies that beat z-score benchmarks on return on turnover.

Figure from the paper full image
abstract click to expand
We develop a signature-based framework for optimal execution in statistical arbitrage strategies with path-dependent predictive signals. Both the alpha process and the trading speed are modelled as linear functionals of the truncated signature of a time-augmented market path, placing signal generation and execution on the same truncated signature basis. This allows the trading rule to react to the realised history of the signal while accounting for temporary impact, inventory exposure, terminal liquidation, and approximate dollar neutrality The main contribution is a quadratic reduction theorem: within the class of signature-linear trading speeds, the restricted path-dependent execution problem becomes a finite-dimensional concave quadratic programme in the policy coefficients. After running synthetic experiments under a mean-reverting log-spread model, we find that the fitted policy achieves a higher return on turnover than a z-score classical threshold benchmark. We shows how the same workflow can be deployed on a historical equity pairs-trading backtest, where the fitted signature policy again outperforms the benchmark in accounting terms.
0
0
q-fin.ST 2026-07-01

Trading strategy dominance varies by market regime

by Krzysztof Ozimek

Regime-Conditional Distributional Comparison of Trading Strategies: A GAMLSS/ZAGA Framework Applied to the S&P 500

GAMLSS/ZAGA model of adjusted information ratios shows SVMP and buy-and-hold superiority depends on volatility and momentum levels.

abstract click to expand
Conventional comparisons of algorithmic trading strategies reduce each performance metric to a single number over the full backtest horizon, thereby discarding information about how performance varies with market conditions. This paper proposes a distributional framework that addresses this shortcoming. A walk-forward backtest of 146 out-of-sample folds on the S&P 500 (2002--2025) is used to compute the Adjusted Information Ratio ($IR^{\ast}$) for a polynomial Support Vector Machine strategy (SVMP) and a buy-and-hold benchmark (BH) in each fold. The resulting $IR^{\ast}$ sequences are modelled jointly via a Generalised Additive Model for Location, Scale and Shape (GAMLSS) with a Zero-Adjusted Gamma (ZAGA) response, with distributional parameters conditioned on market regime covariates: realised volatility and cumulative market momentum. Strategy comparison is conducted through (i) regime-specific differences in expected $IR^{\ast}$ ($\Delta E$) and its variance ($\Delta Var$), derived analytically from the fitted ZAGA parameters, and (ii) parametric bootstrap tests of three null hypotheses concerning $E(IR^{\ast})$, $Var(IR^{\ast})$, and their ratio, evaluated at six representative market regimes. The results demonstrate that the dominance relationship between SVMP and BH is conditional on market regime. The proposed GAMLSS/ZAGA framework constitutes a methodologically rigorous and practically interpretable alternative to conventional strategy evaluation.
0
0
physics.soc-ph 2026-07-01

Social statements map stakeholder ties to balance sheet items

by Takeshi Kato, Yoshinori Hiroi +3 more

Social Statements: A Proposal for a Social-Value Balance Sheet and Profit-Loss Statement

Numerical relationship indicators placed in accounting formats yield equity ratios and margins for social value.

Figure from the paper full image
abstract click to expand
This study proposes a new set of a firm's "social statements" that represent social value, in contrast to conventional financial statements that represent economic value. Financial statements externalize social and environmental costs, and this externalization is one of the primary causes of contemporary social problems. Insights from anthropology, philosophy, and sociology suggest that social value is grounded in social relationships, joint actions, and communication. Building on this understanding, we assign numerical indicators of a firm's social relationships with external stakeholders to the items of a balance sheet and a profit-loss statement as social statements. This approach enables unified measurement units and simplified calculation compared with existing methods for evaluating social impact or social value. Moreover, similar to financial statements, social statements allow firms to be assessed using managerial indicators such as equity ratios and profit margins. The significance of social statements lies in incorporating social value--alongside financial value--into corporate decision-making, and in encouraging social transformation as firms publicly articulate their social value.
0
0
q-fin.RM 2026-07-01

Large deviations generate plausible stress scenarios from sparse data

by Anand Deo

Generating Plausible Stress Scenarios via Large Deviations

The method finds the most probable risk factor setups behind big losses, recovering stressed loss laws where other generators produce no sam

Figure from the paper full image
abstract click to expand
Financial stress tests based on handpicked scenarios can mislead risk management by overlooking genuinely dangerous configurations or overemphasising shocks that are too implausible to be decision-relevant. We develop a systematic method for generating plausible stress scenarios for financial losses driven by exogenous risk factors. The method exploits a large-deviations principle: conditional on a large loss, the risk factors concentrate near the most likely stress configurations. We use this structure to define representative stress distributions and to extrapolate observed samples into more extreme scenarios while preserving the relative plausibility of stress mechanisms. As a result, the procedure can generate informative stress scenarios even when historical data contain few or no observations in the stressed regime. Numerical experiments on two financial network models show that the method recovers the stressed loss law and key stress diagnostics, including in settings where benchmark generators fail to generate any stressed samples.
0
0
econ.GN 2026-07-01

Text model scores papers by proximity to patents

by Paul X. McCarthy, Rasika Amarasiri +1 more

Translation Readiness Index: Measuring Patent-Paper Proximity from Scientific Publication Text

TRI uses title and abstract embeddings to estimate the chance a paper matches past patent-paired work, with external validation at multiple

abstract click to expand
Universities, funders, investors, and policy agencies often need to identify research with translational relevance before patents, licenses, startups, or industry collaborations are visible. This study introduces the Translation Readiness Index (TRI), a text-based measure evaluating a publication's semantic similarity to papers that appear in high-confidence patent-paper pairs. Using 20,610 publications from OpenAlex, including 9,431 publications from the Reliance on Science patent-paper pairs data and 11,179 matched comparison publications, we created paper-level 768-dimensional semantic embeddings from titles and abstracts with SPECTER2. After evaluating four machine learning classifiers, XGBoost achieved the highest ROC-AUC (0.77). We define TRI as the model-estimated probability that a publication belongs to the patent-paper-paired class. Linguistic analysis revealed that patent-paired publications more often use an invention-oriented framing, distinct from the observational language of the comparison group. External validation across University of Western Australia (UWA) publications and leading global universities demonstrated positive associations between high TRI scores and independent translational indicators. TRI provides a text-based method for identifying translation-ready research, though it should be interpreted as a measure of semantic proximity to patented science rather than a direct measure of realized commercialization.
0
0
cs.CL 2026-06-30

LLM markers link explanation quality to forecast accuracy

by Christopher W. Karvetski, Sheldon S. Huang +5 more

Measuring Judgment Quality in Natural-Language Explanations: Evidence from Forecasting Tournaments

Sixty theory-guided patterns scored on 55,000 rationales outperform prior text methods and beat most skill indicators at the forecast level.

Figure from the paper full image
abstract click to expand
Decision-makers routinely rely on expert judgments accompanied by written explanations, yet explanation quality is difficult to measure at scale. Forecasting tournaments offer a natural testing ground: probabilistic judgments are paired with natural-language rationales and scored against realized outcomes. We introduce Explanation Quality Markers (EQMs), a set of sixty theory-guided reasoning patterns scored by large language models (LLMs). In a pre-registered analysis of over 55,000 forecast-rationale pairs from a multiyear forecasting tournament, EQMs predict accuracy at both the forecast and forecaster levels, consistently outperforming pre-LLM text-analysis methods. More than 90% of statistically significant pattern-level EQM-accuracy correlations match our directional hypotheses. The signal is asymmetric: EQMs identify likely underperformers more reliably than they distinguish the very best forecasters. Benchmarked against traditional indicators of forecasting skill, EQMs are the strongest predictor at the forecast level and competitive at the forecaster level, though weaker than prior accuracy. Human ratings of rationale quality are less consistently correlated with accuracy and place disproportionate weight on rationale length. Results transfer to an independent forecasting study. EQMs provide a scalable, interpretable method for extracting judgment-relevant information from written explanations.
0
0
cs.CY 2026-06-30

Agentic AI teams organize via context architecture

by Canhui Liu

The Organizational Behavior of Agentic AI: Collective Intelligence in Human-Agent Workflows

They differentiate work and coordinate interdependence through prompts and memory instead of identity or trust.

Figure from the paper full image
abstract click to expand
Agentic artificial intelligence is increasingly deployed not as a single assistant but as a collective of planners, solvers, reviewers, memory managers, tool users, and orchestrators. These systems are entering organisational workflows under familiar labels such as teams, managers, committees, markets, and workflows. This article asks whether such agent collectives exhibit organisational behaviour in a sense that is analytically comparable to, yet distinct from, human organisational behaviour. I argue that agentic AI is a partial organisational analogue. It resembles a human organisation because it differentiates work, coordinates interdependence, performs recurrent routines, crosses boundaries, and produces collective outcomes. It differs because these patterns are not sustained by motivation, identity, trust, employment, socialisation, or moral accountability. They are sustained by context architecture: prompts, memory, traces, schemas, tools, validators, and permissions. The article develops contextual transaction cost as the central mechanism linking these similarities and differences. Computational theorising, synthetic task simulations, real LLM agent traces, and robustness analyses show that human-imitation forms often underperform when they add lossy handoffs, correlated deliberation, and verification burdens, whereas shared-state and adaptive forms perform better when they make context durable, inspectable, and task-contingent. The article contributes to organisation studies by theorising agentic AI as an emerging object of organising and by specifying the interface conditions under which human and agentic organisational behaviour can jointly support collective intelligence.
0
0
econ.TH 2026-06-30

Sum-minimization locates efficient multi-agent insurance

by Zijun Meng

Pareto Efficient Insurance with Multiple Policyholders, Multiple Insurers, and Multiple Indemnity Environments

Pareto optimal contracts with many policyholders and insurers across indemnity types reduce to one aggregate minimization problem.

abstract click to expand
This paper proves a sum-minimization characterization of Pareto efficient insurance with multiple policyholders, multiple insurers, and multiple indemnity environments. We also provide a result regarding the pairwise implementability of the policyholder- and insurer-aggregate level arrangements in the multiple policyholders and multiple insurers setting.
0
0
cs.CY 2026-06-30

AI-exposed firms earn 64 bp weekly return premium

by Nicola Borri, Yukun Liu +1 more

AI Premium

Stocks that covary with real AI token growth outperform, with the premium extending to consumer sectors but absent in China.

Figure from the paper full image
abstract click to expand
Using 380 trillion tokens of realized AI consumption across more than four hundred large language models from the licensed proprietary OpenRouter dataset covering approximately 2 percent of current global monthly AI token consumption, we analyze how AI affects firms, markets, and workers. Leveraging the unprecedented size, scope and granularity data, we construct the AI Factor from growth in tokens, dollars, and users, estimate firm-level AI Betas from stock return comovement, and characterize the AI Premium. First, we build a high-frequency AI factor and decompose it into salient components. Second, we show that firms whose returns covary more positively with the AI factor--high AI beta firms--earn higher subsequent returns, and the AI premium is large and heterogeneous. A value-weighted long-short strategy earns 64.1 basis points per week, and the premium is large for loadings on the intensive, frontier-oriented margin of AI consumption-closed-source models, paying and seasoned users, and long prompts--but not on casual or open-weight use. Third, the premium reaches beyond technology firms into consumer-facing and capital-heavy parts of the economy, but is absent in emerging markets, including China. Fourth, the AI exposure is more positive in nonroutine interactive work and the more negative in analytical, scientific, and operations-control skills--an occupation one standard deviation higher in interaction-and-communication content has 0.36-standard-deviation higher market-implied AI premium. Additionally, we provide early evidence of the rise of the agentic economy.
0
0
cs.CL 2026-06-30

Randomizing field order in training cuts order-change penalty from 7.4 to 0.2 nDCG points

by Aivin V. Solatorio, Olivier Dupriez +1 more

Field Order Should Not Matter: Permutation-Invariant Embedding Model Fine-Tuning for Structured Metadata Retrieval

Standard fine-tuning makes retrieval depend on serialization order; PI-FT binds meaning to labels instead and works on a new 15-language ben

Figure from the paper full image
abstract click to expand
We study retrieval over catalogs of structured metadata, where each record is a small schema whose fields answer different kinds of query. Embedding a record with a text encoder first serializes its fields into a string, which forces a choice of field order. We show this choice, usually treated as an implementation detail, silently controls retrieval quality once the encoder is fine-tuned. A standard fine-tune loses 7.4 nDCG@10 points when the index is rebuilt under a different field order, because it reads absolute position instead of the field labels. We propose permutation-invariant fine-tuning ($\textbf{PI-FT}$), which serializes each record under a freshly sampled field order with random field dropout, so meaning binds to the labels rather than to position. The change is about two lines in the data loader; it costs negligible in-distribution accuracy and cuts the order-change penalty to 0.2 points. We study this in the discovery of development statistics, a catalog of nearly 10,000 indicators that should be searchable in many languages by a model small enough to self-host. As AI assistants and agents increasingly mediate access to public data and statistics, this retrieval step decides whether an answer is grounded in the right indicator or series, making discoverability a precondition for disseminating data through AI. Because usage logs cannot provide training signal for indicators no one has searched, we generate the queries instead. $\textbf{DevDataBench}$ is a fully LLM-generated benchmark of grounded, facet-targeted queries across 15 languages, covering every indicator for both training and evaluation. A fine-tuned 118M-parameter CPU encoder outperforms every zero-shot baseline, including $\texttt{text-embedding-3-large}$ (0.707 vs.\ 0.556 nDCG@10), with the largest gains in low-resource languages. We release the benchmark, pipeline, models, and a reusable PI-FT framework.
0
0
econ.GN 2026-06-30

Swiss road cartel mimicked competition to hide 45% overcharges

by David Imhof, Thierry Madiès +1 more

Swimming in Dark Water: When Cartels Mimic Competition

Cost-based allocation under a formal convention allowed evasion of standard detection methods.

abstract click to expand
This paper analyzes the internal organization and economic effects of a bid-rigging cartel in the road construction sector of the Swiss canton of Ticino, active from 1999 to 2005. Using exceptionally rich documentary evidence, we reconstruct how cartel members coordinated bids and allocated contracts under a formal agreement known as the 'convention'. We show that, despite the absence of side payments, the cartel implemented a cost-based allocation mechanism that closely approximated the first-best collusive outcome. Regression and machine-learning analyses indicate that observable cost proxies systematically predict both winning bids and bid rankings. The evidence further suggests that cartel members strategically mimicked competitive bidding behavior, allowing them to evade standard econometric detection methods. Using double machine learning, we estimate average overcharges of at least 45\%, and potentially substantially higher, highlighting the significant financial harm caused by this sophisticated form of collusion.
0
0
econ.GN 2026-06-30

Bank earnings shocks lift Canadian output via credit supply

by Santiago Camara, Sanaa Latif

Bank Earnings, Credit Supply & the Macroeconomy: Evidence from Canada

Purged net-worth surprises from the six large banks reduce spreads and raise real activity over the medium run.

Figure from the paper full image
abstract click to expand
This paper studies whether news about banks' balance sheets propagates to aggregate financial conditions and macroeconomic activity. We construct high-frequency Canadian bank net-worth shocks using stock-price reactions around earnings announcements of the six large Canadian banks. Guided by a model in which higher intermediary net worth expands credit supply and lowers borrowing spreads, we use the co-movement between bank equity prices and Canadian corporate spreads to purge raw bank equity surprises from contaminating information. Favorable purged credit-supply bank net-worth shocks lower corporate spreads, raise bank valuations and broader equity prices, appreciate the Canadian dollar, and increase real activity over the medium run. The results are robust across specifications, samples, and additional outcomes, and suggest that bank earnings news is macroeconomically relevant in concentrated banking systems.
0
0
q-fin.RM 2026-06-30

VaR restricts risk reduction to none

by Wing Fung Chong

Strategic Risk Reduction: Self-Protection and Self-Insurance

Tail Value-at-Risk instead creates non-convexity solved by marginal-balance isoquants in the same Bernoulli setting.

abstract click to expand
This paper studies how a risk holder should combine self-protection and self-insurance when market insurance is absent. In a Bernoulli loss model, self-protection reduces the residual loss probability, while self-insurance reduces the residual loss severity. The risk holder evaluates residual risk using either Value-at-Risk or Tail Value-at-Risk and incurs a joint risk-reduction cost that allows technological interaction between the two activities. We show that Value-at-Risk leads to a threshold-driven solution that the optimal strategy is either no risk reduction, pure self-protection, or pure self-insurance. By contrast, Tail Value-at-Risk creates a direct interaction between residual frequency and residual severity, making the problem non-convex even in the Bernoulli setting. We solve it using an isoquant geometry method based on the marginal-balance curves for self-protection and self-insurance. The analysis identifies when optimal strategies lie on boundaries, extreme constrained candidates, touching components, or crossing components, and shows how the confidence level and the cost technology determine whether self-protection and self-insurance behave as substitutes or complements.
0
0
physics.app-ph 2026-06-30

Collective PV sharing cuts needed capacity and raises savings

by Ana B. Cristóbal (0000-0002-4314-6160), Daniel Sierra +3 more

Decision-support strategies for photovoltaic self-consumption under declining electricity prices and limited remuneration of surplus generation

In tests with 24 rural users, internal coordination matched subsidies for investment under falling prices and low surplus pay.

abstract click to expand
The success of distributed photovoltaics may be undermining its own future. As solar penetration increases, electricity prices decline during periods of peak generation, reducing the value of surplus photovoltaic production. This raises a critical question: can citizen-led energy systems remain economically viable in electricity markets dominated by renewable generation? Rather than exploring technically optimal but institutionally unrealistic solutions, we examine the options available under current regulatory and market conditions. Using high-resolution consumption data from a rural community sharing a PV facility among 24 users, we identify pathways for long-term sustainability. The study makes two contributions. First, it shows that effective internal coordination can mobilize participation and investment as successfully as external subsidies. Second, it compares static, dynamic, and hybrid energy-sharing models, with and without storage, providing a flexible framework that balances efficiency, fairness, and governance. Results show that collective self-consumption reduces required PV capacity, lowers investment costs, and increases annual savings compared with individually operated systems. Alternative allocation schemes further improve benefit distribution and local electricity use, although gains depend on trade-offs between efficiency, fairness, and governance complexity. Under current electricity prices and remuneration schemes, battery storage provides limited additional economic value and becomes attractive only under specific market conditions. Overall, the long-term viability of citizen-led photovoltaic initiatives depends less on technological sophistication than on collective coordination and adaptive governance.
0
0
q-fin.RM 2026-06-30

Hidden dependence preserves worst-case tail risk bounds

by Corrado De Vecchi, Max Nendel +1 more

Hidden Dependence and Aggregate Tail Risk

Small perturbations of the joint distribution that keep marginals fixed match the risk limits from full dependence uncertainty for gamma-tai

Figure from the paper full image
abstract click to expand
We study risk aggregation problems for arbitrary non-decreasing aggregation functions and tail risk measures under dependence uncertainty in a distributionally robust setting. To this end, we introduce the notion of hidden dependence for random vectors, which is built on the concepts of risk concentration and common tail events developed in Wang and Zitikis (2020). We show that, starting from a tail event $A$ of the aggregate loss for an arbitrary random vector $Y$, one can construct a random vector with hidden dependence that dominates $Y$ on the tail event $A$. We then focus on the case in which model uncertainty is described by small perturbations of the distribution of a random vector with respect to a suitable probability distance without changing the marginals. We show that these perturbations of the reference distribution are compatible with hidden dependence and thus lead to the same worst-case risk bounds as in the unconstrained case for arbitrary $\gamma$-tail risk measures with a suitable level $\gamma$. Finally, we apply our results in a credit risk context and quantify the potential underestimation of portfolio risk arising from uncertainty in the dependence structure. In particular, we show that even small deviations from a reference Gaussian dependence model can, in principle, justify dramatic increases in capital requirements.
0
0
cs.CL 2026-06-30

LLM surrogates overstate liking and flatten human taste patterns

by Xiangyu Ma, Mengmi Zhang +2 more

Not-quite-human tastes: the stylized omnivorousness of LLM survey surrogates

Silicon samples from three model families inflate reports, erase correlations, and distort links to age, class, gender and race in arts data

Figure from the paper full image
abstract click to expand
Large-language models have proven to be remarkable if inconsistent parrots of public attitudes and opinions. The extent to which LLMs are able to produce reasonable approximations of cultural taste remains an open empirical question that becomes more urgent by the day, with market research companies already offering provisional `synthetic' survey panels and the contamination of standard survey data from LLM-generated responses. In this study, we build on past work on silicon sampling by extending considerations of its algorithmic fidelity and alignment to the domain of cultural consumption. We use large-language models from OpenAI, Anthropic, and DeepSeek to each produce 277,470 (30x9249) silicon surrogates of survey respondents from the Survey of Public Participation in the Arts (SPPA). We find these silicon surrogates' tastes to be highly stylized facsimiles of human tastes. (1) Silicon samples have a systematic postive-bias for liking, resulting in inflated ecological estimates of tastes. The individual-level bias of silicon samples are not well-explained by the WEIRD-bias often discussed in the literature. (2) The complex relationality in real taste structures is completely lost among silicon samples. (3) Finally, very little of the known cultural alignment between tastes and social space are preserved. Silicon samples attenuate age-taste associations, resurrect anachronistic class-taste associations, caricaturize gender- and race-taste associations.
0
0
q-fin.MF 2026-06-30

Convex risk measures turn resilience into worst-case adjusted drift

by Matteo Ferrari, Roger J. A. Laeven +2 more

Financial Resilience Evaluation: From Conditional Expectations to Dynamic Convex Risk Measures

When induced by a Lipschitz or quadratic BSDE driver, the evaluation of price increments equals the infimum over zero-penalty measures of an

abstract click to expand
Financial resilience concerns the rate at which a position recovers, or further deteriorates, in response to adverse conditions. As a first step, Laeven, Ferrari, Rosazza Gianin, and Zullino (arXiv:2505.07502) introduced the resilience rate, defined as the expected instantaneous rate of (favorable) change of a price or risk-assessment process. Since this quantity captures only the conditional mean of future increments, it cannot distinguish between positions having the same expected recovery but different conditional risk profiles. We obtain a richer characterization by evaluating such increments through a genuine, possibly nonlinear, dynamic risk measure. More precisely, for an It\^o process $\pi$ and a normalized, cash-additive dynamic risk measure $\rho$, we define the resilience evaluation by \[\mathcal D_s^\rho\pi_t := L^1\text{-}\lim_{\varepsilon\to0^+} \frac{1}{\varepsilon}\rho_s(\pi_{t+\varepsilon}-\pi_t), \qquad 0\leq s\leq t<T,\] whenever the limit exists. When $\rho$ is a convex dynamic risk measure induced by a BSDE with a Lipschitz or quadratic driver, we prove that this limit is well-posed and admits an explicit dual representation. It is given by the worst-case conditional expectation, over a zero-penalty class of measure changes, of an effective drift combining the drift of $\pi$ with the risk adjustment assigned by $\rho$ to its volatility. We further establish attainment of the optimal scenario and illustrate the scope of the construction, as well as the role of the assumptions, through examples and counterexamples.
0
0
cs.LG 2026-06-30

Output heads dominate backbones on fat-tailed returns

by Sichao He, Yansong Zhang

Heads, Not Backbones: Output Heads Dominate Architectures on Fat-Tailed Returns

Mixture heads improve CRPS by 3.7 points over backbones at short horizons in S&P 500 tests.

Figure from the paper full image
abstract click to expand
In a deep forecasting pipeline for fat-tailed financial returns at short horizons, which matters more - the backbone architecture or the output head? We compare four modern backbones (TimesNet, DLinear, N-BEATS, iTransformer) under three output heads: a point head, a single-Gaussian density head, and a Gaussian mixture density head with K=4 components. On S and P 500 monthly log-returns (1871-2023) under anchored walk-forward validation, the three heads form a strict gradient: switching from point to Gaussian improves CRPS by about 1.3 percent; switching from Gaussian to mixture adds a further about 2.4 percent. Switching between backbones, in contrast, changes CRPS by less than 1.5 percent on the point-head row and on the backbone-mean axis; density-head backbone spread is larger (up to 5.1 percent on the h=1 Gaussian row, driven by N-BEATS) but the head gradient (3.7 percentage points) still dominates. The Model Confidence Set on squared errors does not exclude any of the 12 variants at the 5 percent level: the head separates them only on distributional metrics (CRPS, pinball, coverage), not on squared error. The mixture head incremental value over a single Gaussian is largest in the highest-volatility regimes (13.9 percent in 1970s stagflation at h=12), confirming the mixture captures tail risk beyond what a unimodal Gaussian can express. The picture is horizon-dependent: the head dominates at short horizons, but at long horizons (h >= 6) the backbone re-takes the lead - an h-split we document against classical baselines (section 5.1). We conclude that on fat-tailed returns at short horizons, the head dominates the backbone, and the mixture distribution adds genuine value over a single Gaussian during crisis periods when risk-management decisions actually matter.
0
0
cs.CL 2026-06-30

Fund data builds advisor personas that recover real portfolio moves

by Suhwan Park, Hoyoung Lee +6 more

Fund2Persona: A Framework for Building and Refining Financial Advisor Personas from Fund Disclosure Data

Grounded personas match manager decisions on unseen holdings and give more specific advice than generic prompts.

Figure from the paper full image
abstract click to expand
Demand for personalized financial advising is growing, but consistent advisor expertise is difficult to obtain, scale, and encode in LLM systems. Simple persona prompts rarely specify how a financial advisor should reason and often drift toward generic recommendations. We propose Fund2Persona, a framework that grounds financial-advisor personas in fund disclosures, holdings transitions, market context, and manager commentary, then refines them through an agentic actor--scorer--patcher loop. We evaluate the resulting personas on held-out holdings-transition reconstruction and manager-commentary alignment, where they better recover portfolio decisions and grounded manager interpretation than generic baselines. We further study two downstream diagnostics: market-scenario generation, where persona retrieval broadens plausible investment views beyond repeated generic rollouts, and advisory dialogues grounded in investor profiles, where matched personas give more specific and useful advice than a generic advisor. These results suggest that fund-data-grounded financial-advisor personas can make manager-specific investment expertise portable rather than merely changing an LLM's surface style.
0
0
cs.AI 2026-06-30

CLQT benchmark maps LLM trading agent skills instead of ranking by returns

by Bo Qu, Mingguang Chen

CLQT: A Closed-Loop, Cost-Aware, Strategy-Consistent Benchmark for Diagnostic Evaluation of LLM Portfolio-Management Agents

Closed-loop five-stage cycles and APM-CS scoring separate market outcomes from agent coherence, acuity, and discipline.

Figure from the paper full image
abstract click to expand
LLM agents are increasingly cast as autonomous portfolio managers, and benchmarks have moved from financial question-answering to sequential trading. Yet most still rank agents by returns over a fixed window -- a weak proxy, since a period's return is dominated by the market path and apparent alpha can dissolve once look-ahead leakage is controlled. Such a ranking certifies neither sound reasoning, nor a consistent strategy, nor a durable edge. We introduce CLQT, which reframes closed-loop trading evaluation as diagnosis rather than ranking: an instrument that localizes where and why an agent's process succeeds or fails. CLQT is a fully closed-loop, cost-aware, strategy-consistent, temporally-gated environment whose agents run a five-stage cycle: gather, synthesize, allocate, execute, reflect. Each round emits a complete DecisionRound sealed into a recompute-verifiable hash chain, so every metric is reconstructable from the trail. Six pillars form the substrate: a hard TimeGate, institutional transaction- and financing-cost modeling, strategy-consistency scoring, three-tier memory, a Model-Context-Protocol tool layer, and mandate-aware synthesis. The same agent runs as a constrained committee of specialized roles or a single full-autonomy orchestrator, making process scaffolding an experimental variable. From the audit trail we compute a five-axis capability scorecard (APM-CS: Coherence, Acuity, Composure, Discipline, Reliability), with Coherence judged partly by a held-out, out-of-cohort LLM to curb self-preference bias. We validate it on a contamination-controlled multi-model backtest with an ablation grid and a live broker track on unseen, post-cutoff data, against a repeated-run noise floor. CLQT separates outcome from capability, yielding not a model ranking but a durable, extensible map of agent competencies and limitations.
0
0
q-fin.TR 2026-06-29

SPY lag-1 autocorrelation stems from magnitude

by Victoria Portnaya

The Bounce Has No Direction: Sign, Magnitude, and the Microstructure of Equity Return Predictability

A decomposition isolates magnitude shrinkage as the sole driver, matching bid-ask bounce rather than directional reversal.

abstract click to expand
SPY's lag-1 return autocorrelation ($\hat\rho(1)=-0.081$, $z=-7.4$) is among the most significant regularities in empirical equity finance, yet the standard variance-ratio (VR) test cannot determine whether it reflects directional reversal or magnitude shrinkage - phenomena with entirely different trading implications. We develop the Fourier-Residue Identity (FRI), which decomposes return autocorrelation into a sign ($k=2$) and a magnitude ($k=4$) channel, each independently testable and neither redundant. Applied to six US instruments over 1993--2026 and a 21-instrument cross-asset panel, the FRI delivers a sharp microstructure diagnosis. The lag-1 autocorrelation in SPY is driven entirely by magnitude: the FRI sign test is insignificant ($p=0.11$) while the full test achieves $p<10^{-12}$. A large move yesterday predicts a smaller move today regardless of direction - the fingerprint of bid-ask bounce and non-synchronous constituent staleness, not directional reversal. At lag 3, a significant directional reversal ($p=0.02$) invisible to the scalar ACF reveals a separate partial-price-adjustment channel. We prove the Fejer identity VR(q)=1+2C_q (confirmed to <0.001 on all series), giving the Lo-MacKinlay test a spectral interpretation, and introduce a subsample diagnostic R_N=G_{N/2}/G_N that classifies equity autocorrelation as structural (R_N->1) rather than sampling noise (R_N->sqrt(2)). The cross-asset panel shows mean reversion confined to exchange-traded equities and sovereign bonds; credit ETFs, commodities, FX, and crypto are indistinguishable from random walks. All estimators pass 27 unit tests; Monte Carlo confirms correct 5% size under GARCH.
0
0
q-fin.MF 2026-06-29

Valuation rules recover their generating uncertainty structures

by Jongjin Park, Hyungbin Park

Valuation Reveals Uncertainty

Observed dynamic sublinear valuations allow explicit identification of latent models and nonparametric estimation from limited data.

Figure from the paper full image
abstract click to expand
This paper studies the recovery of uncertainty from dynamic sublinear valuation rules. A robust valuation assigns each payoff its worst-case expected value across plausible models under uncertainty and induces a dynamic sublinear valuation rule. While valuation rules are observable in practice, the underlying uncertainty structure is latent. First, we show that the latent uncertainty structure can be identified from an observed valuation rule and provide an explicit procedure for recovering it. Second, we develop the notion of time consistency for uncertainty structures as the uncertainty-side counterpart of time consistency in valuation. Third, we characterize all time-consistent uncertainty structures that represent a given valuation rule. Finally, we develop nonparametric estimators for recovering uncertainty from limited valuation data. These results overturn the traditional Knightian view that uncertainty is inherently non-measurable. Indeed, valuation contains sufficient information to identify, characterize, and statistically recover the uncertainty structures that generate it.
0
0
q-fin.RM 2026-06-29

Bayesian POMDP beats heuristics at allocating AI decision authority

by Matthew Francis Dixon

Adaptive AI Delegation under Uncertainty: A Bayesian Governance Policy for Sequential Decision Authority

Sequential updates on evidence quality let the policy adjust delegation levels across changing AI regimes where fixed rules lose performance

Figure from the paper full image
abstract click to expand
Organizations increasingly use large language models and agentic AI systems to generate probabilistic assessments and candidate actions in high-consequence settings. This creates a managerial problem distinct from prediction: how should organizations allocate decision authority to AI-generated recommendations as evidence quality, uncertainty, and organizational objectives evolve over time? Existing AI governance frameworks emphasize transparency, documentation, oversight, and regulatory compliance, but provide limited quantitative guidance for dynamically allocating decision authority under uncertainty. To address this challenge, we formulate adaptive AI delegation as a Governance-Aware Partially Observable Markov Decision Process (POMDP) in which Bayesian inference estimates the informational state and sequential optimization determines delegated AI authority. The paper also develops a quantitative validation and benchmarking framework for governance policies. Synthetic stress tests, reported LLM-confidence robustness, forecast-accuracy validation, governance-appetite sensitivity, and fragile-AI early-warning experiments evaluate whether the proposed policy exhibits graceful degradation, robustness to confidence-only perturbations, adaptive delegation under improving evidence quality, and interpretable calibration of institutional conservatism. The Governance-Aware POMDP is further benchmarked against five representative governance strategies operating under identical Bayesian beliefs, information, and governance objectives. The results show that while specialized heuristics perform well in stationary settings, sequential Bayesian governance provides the strongest general-purpose governance policy across heterogeneous AI-quality regimes by adaptively allocating organizational decision authority under uncertainty.
0
0
econ.GN 2026-06-29

Bayesian optimization certifies equilibria via Negishi weights

by Felix Kubler

Bayesian Optimization on the Equilibrium Manifold

The low-dimensional parameterization lets the method locate optimal policies like carbon taxes with high-probability guarantees in heterogen

Figure from the paper full image
abstract click to expand
Computing optimal policy in heterogeneous-agent economies is complicated by the possibility of multiple equilibria. We overcome this difficulty by showing that when the equilibrium manifold has a low-dimensional Negishi-weight parameterization, Bayesian optimization reliably finds approximate solutions and can be used to certify candidate solutions with high probability. This insight brings recent machine learning advances to bear on a core problem in macroeconomics. We apply Bayesian optimization to a dynamic economy with heterogeneous agents and climate change and compute optimal carbon taxes in this setting. Although in principle the presence of the carbon externality creates scope for multiple equilibria, we show that in an example with realistic calibration of damages competitive equilibra are most likely unique.
0
0
q-fin.PR 2026-06-29

Supply chain propagation turns text embeddings into 0.86 Sharpe predictor

by Asef Y{i}lk{i}

Supply Chain Propagation of Textual Signals: LLM Embeddings and Cross-Sectional Return Predictability

Network-augmented signals from 10-K reports deliver 7.27 percent annual alpha after Fama-French five factors.

Figure from the paper full image
abstract click to expand
This paper proposes a novel asset pricing framework that augments large language model (LLM) embeddings of annual report disclosures with supply chain knowledge graph (KG) propagation. Using FinBERT embeddings of 10-K MD&A sections for 255 S&P 500 firms over 2011-2025, two sets of return predictors are constructed: direct LLM embeddings and network-augmented embeddings, where firm-level signals propagate through inter-firm linkages. Fama-MacBeth cross-sectional regressions reveal that the network-augmented factor (net_pc_5) carries significant return predictability with a Newey-West t-statistic of -2.64, even after controlling for momentum, volatility, and firm size. A long-short portfolio sorted on net_pc_5 achieves an annualized Sharpe ratio of 0.86 and a Fama-French five-factor alpha of 7.27% per year (t = 2.30). The predictive power survives out-of-sample tests, placebo experiments, sector-neutralization, and subsample analysis. The findings suggest that inter-firm network structure contains pricing-relevant information beyond firm-level textual disclosures.
0
0
cs.AI 2026-06-29

LLM summaries of financial reports can flip investment decisions

by Hoyoung Lee, Suhwan Park +16 more

When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial Analysis

Even fluent and plausible compressions of filings and transcripts change the decisions supported by the originals.

Figure from the paper full image
abstract click to expand
Financial decision-makers face more information than they can directly inspect, making context compression necessary. Yet when large language models (LLMs) compress financial source material, they can alter the investment judgment supported by the original source. We frame this problem as information fidelity: compression loses fidelity when it changes the decision induced by the source. In agentic systems, such losses may recur across intermediate steps and amplify throughout the decision process. Across financial filings and earnings-call transcripts, we find that LLM-based compression can produce fluent and factually plausible compressed contexts that nevertheless alter downstream decisions. We analyze two diagnostic patterns associated with fidelity loss: decontextualization, where salient evidence is retained but separated from the caveats and contextual qualifiers needed for correct interpretation, and model dependency, where different compressors expose different views of the same source. We then propose Agentic Context Compression, which generates multiple candidate compressions and audits their disagreements against the original source. Our results suggest that financial compression should be evaluated not only by efficiency or factuality, but also by its ability to preserve decision-relevant context.
0
0
econ.GN 2026-06-29

AI adds tacit machine knowledge to Nonaka's innovation spiral

by Aaron Chatterji, Daniel Rock +1 more

The Human-Machine Knowledge Spiral

The company's role stays the same: create shared context where human and machine knowledge convert and amplify each other.

abstract click to expand
Nonaka emphasized that innovation is the result of a continuous back-and-forth between tacit and explicit knowledge. Artificial intelligence introduces a fundamentally new object into this process -- tacit machine knowledge -- but Nonaka's ideas are more relevant than ever. The central role of the knowledge-creating company remains the same: to create the shared context in which different kinds of knowledge can feed off each other, become organizational knowledge, and set off further cycles of innovation.
0
0
econ.GN 2026-06-29

70% oilseed export cut to China triggers 3.27% global loss

by Diksha Gupta, Ritwick Mishra +3 more

Cascading Impacts of the USA--China Trade War on Global Oilseed Supply Chain

Model shows China hit hardest at 14%, but Brazil reallocation halves the worldwide damage to 1.36%

Figure from the paper full image
abstract click to expand
Global supply chains are highly interconnected, making them vulnerable to cascading disruptions induced by trade policy shocks. Understanding how such disruptions propagate through production networks, and how mitigation mechanisms such as trade reallocation and production adjustment can alleviate their impacts, remains a central challenge. In this work, we develop a linear programming formulation of an Input-Output (IO) system that captures cascading supply-chain disruptions together with trade reallocation and production expansion. Our formulation yields a system-level equilibrium characterization that enables the joint analysis of disruption propagation and mitigation within a unified framework. We propose an efficient algorithm for computing approximate equilibrium solutions by minimizing total unmet demand in large IO systems. We apply our approach to tariff-induced disruptions in the global oilseeds supply chain arising from the U.S.-China trade war. Our results show that a localized 70% disruption to flows from the U.S. oilseeds sector to China leads to a 3.27% loss in global output, with China experiencing a disproportionate loss of 14.02%. As a counterfactual mitigation strategy, allowing a 20% reallocation from Brazil's oilseed sector to China significantly reduces global output losses to 1.36%, although pressure remains high on final-demand flows. We further investigate production expansion as an additional mitigation mechanism and show that it introduces tradeoffs between reducing global final-demand losses and protecting Brazil's domestic flows. Domestic reallocation disproportionately shifts losses toward smaller economies, while globally sourced expansion redistributes losses more broadly across the network.
0
0
math.PR 2026-06-29

Weighted approximations improve right-tail fits for lognormal sums

by Chunle Huang

Comonotonic and moment matching approximations for sums of lognormal random variables

New methods based on weighted distributions are both comonotonic and moment-matching while outperforming classical versions in the right tai

abstract click to expand
In this paper, based on the concept of weighted distribution, we introduce a kind of new approximations for sums of lognormal random variables, such that they are both comonotonic and moment matching. Numerical results show that the approximation performance of the newly presented approximations is, overall, comparable to the classical comonotonic approximations, but in terms of the right tail of the distribution of the original sum our approximations perform better than the classical comonotonic ones. Another contribution of this article is the establishment of the step-weighting theory for continuous random variables.
0
0
cs.AI 2026-06-29

Mobility flips AI skill investment to top workers

by Simrita Singh, Naireet Ghosh +1 more

Managing the Human Fallback: Skill Investment Under Improving AI and Worker Mobility

Firms shift from training the least-skilled to the most-skilled below the AI level when workers can switch jobs.

abstract click to expand
When firms deploy autonomous AI, they must decide how much work to leave to the system and how much to keep workers engaged. This decision affects current output and future human capital. We develop a parsimonious two-period model in which AI may outperform the worker when it functions, but may fail with positive probability. A firm chooses worker engagement; engagement lowers current output for below-benchmark workers, but changes future skill through learning and erosion. We distinguish two dimensions of AI progress: capability, the system's output when it works, and reliability, the probability that it works. In a single-firm benchmark, engagement is valuable only as fallback investment. The firm engages the least-skilled workers most, because they have the largest skill gaps and are least costly to bring toward a useful fallback level. With worker mobility, engagement also affects labor-market sorting: workers prefer jobs that build more valuable skill trajectories. This sorting motive targets higher-skill workers near the AI frontier, where skill gains are more valuable and engagement is less costly. Mobility can therefore reverse the engagement pattern, shifting investment from the least-skilled toward the most-skilled workers below the AI benchmark. Mobility also reshapes how AI progress affects engagement: greater capability raises engagement by increasing the value of the skill trajectory a firm offers, whereas greater reliability can raise or lower it because it reduces fallback need while also changing learning opportunities. Under worker mobility, human-AI work design becomes a problem of human-capital investment, in which allocating work today shapes future skill.
0
0
econ.GN 2026-06-29

Green leadership drives sustainable nursing practices

by Thabit Atobishi, Saeed Nosratabadi

Green Transformational Leadership and Sustainable Nursing Practices: Evidence from the Healthcare Sector

Survey of 760 nurses finds ethical climate and green transformational leadership increase eco-friendly behaviors, weakened when hypocrisy is

Figure from the paper full image
abstract click to expand
The healthcare sector contributes approximately 4.4% of global greenhouse gas emissions, yet research on the organizational determinants of sustainable behaviors among healthcare workers remains limited. This study examines how green transformational leadership and ethical climate influence sustainable clinical behaviors among registered nurses, with green psychological climate as a mediator and perceived organizational hypocrisy as a moderator. Data were collected from 760 nurses across 11 public and private hospitals in Jordan using a cross-sectional survey design. Structural equation modeling with bootstrapping was employed to test the hypothesized relationships. The results revealed that both green transformational leadership and ethical climate positively predicted sustainable clinical behaviors. Green psychological climate partially mediated both relationships. Perceived organizational hypocrisy significantly weakened the positive effects of green transformational leadership and ethical climate on sustainable behaviors. The model explained 35.7% of the variance in sustainable clinical behaviors. These findings highlight that fostering sustainability in healthcare requires not only supportive leadership and ethical organizational environments but also authenticity and consistency between stated values and actual practices. The study extends green transformational leadership theory to healthcare settings, integrates ethical climate research with environmental sustainability, and introduces perceived organizational hypocrisy as a critical boundary condition. Practical implications for healthcare administrators seeking to reduce their environmental footprint are discussed.
0
0
econ.EM 2026-06-29

Regret statistic classifies algo liquidity demand from data alone

by Irene Aldridge

Liquidity-Based Audit of Algorithmic Trading Strategies

Trade and price history recovers informed-trader versus market-maker distinction for linear strategies

abstract click to expand
We show that net demand for liquidity by algo strategies is identifiable from its trade and price history alone, with no knowledge of its signal or optimization problem. An exact multi-period regret decomposition implies that the sign of this statistic classifies a linear strategy as a net liquidity consumer or provider, recovering the Kyle (1985) informed-trader/market-maker dichotomy from observables alone. Under an AR(1) cost process, the same statistic equals the product of strategy size and the squared Roll (1984) implied spread, making the correction a direct proxy for prevailing illiquidity. Extending to endogenous price impact and aggregating across N correlated strategies yields a liquidity-balance condition whose violation produces welfare loss scaling as N squared, a closed-form fire-sale externality. We calibrate to CRSP equity data (2016-2025), tracking implied spreads through the COVID-19 and 2022 rate-shock episodes, with an estimator computable in O(Tnd) time.
0
0
econ.GN 2026-06-29

Negative priority-demand correlation makes topping up reduce redistribution

by Zi Yang Kang, Mitchell Watt

Topping Up and Optimal Redistribution

The planner's nonlinear schedule loses power to target high-priority consumers when they have lower demand.

Figure from the paper full image
abstract click to expand
This paper studies how topping up -- allowing recipients of in-kind transfers to supplement subsidized consumption in a private market -- affects optimal redistribution. Consumers can access a competitive private market, while a social planner offers an alternative nonlinear price schedule. We show that the effect of topping up depends on the correlation between redistributive priority and demand. When the correlation is positive, topping up does not affect the optimal mechanism. When the correlation is negative, topping up weakens screening and reduces redistribution. At the extensive margin, topping up reduces the set of environments in which intervention is optimal. At the intensive margin, topping up weakly reduces both the scope of a free public option and the mass of consumers served, and shifts redistribution away from the consumers with the highest redistributive priority. We characterize the optimal mechanisms and show how topping up changes the comparative statics of optimal redistribution with respect to redistributive priorities.
0
0
q-fin.MF 2026-06-29

Forward-curve hedging error splits into bucket

by Riccardo Alberti, Sven Karbach

Hedging Maturity-Specific Risk in Forward Curve Derivatives under Stochastic Volatility

Exact decomposition holds under infinite-rank stochastic volatility in the HJMM framework, with residual acting as volatility floor in enlar

Figure from the paper full image
abstract click to expand
We study the variance-optimal hedging of European contingent claims written on forwards. We assume that the dynamics of the underlying forward curves follow a Heath--Jarrow--Morton--Musiela stochastic partial differential equation modulated by an infinite-rank stochastic covariance component. The variance-optimal hedge is then given by the Galtchouk--Kunita--Watanabe projection with respect to some covariance-norm quotient generated by the forward curve martingale. We show density of finite-maturity and delivery-window strategies, convergence of spectral finite-rank hedge projections and an exact decomposition of the quadratic hedging error into bucket, rank and residual risk components. In enlarged filtrations, the residual risk is a stochastic-volatility floor for claims loading on non-traded covariance noise. We illustrate the hedging framework in affine stochastic covariance and multiplicative HJMM models, and give a concrete example of the decomposition in a CIR stochastic covariance model.
0
0
math.PR 2026-06-29

Hawkes processes close under finite linear signature dynamics

by Miquel Noguer i Alonso

A General Theory of Paths: Signatures, Jump Lifts, and Expected Signatures of Self-Exciting Processes

State-weight augmentation produces closed equations for expected signatures and recovers excitation parameters in the scalar case.

Figure from the paper full image
abstract click to expand
This paper develops a path-first theory using the signature as a universal coordinate for deterministic paths, rough paths, jump streams, and path-valued random variables. Geometricity is presented as a first-order algebraic property with second-order obstructions: a bracket for non-geometric lifts, and a covariance when averaging random paths. This framework links the shuffle identity, Marcus-Ito distinction, expected signatures, signature kernels, and free nilpotent group geometry. We offer four main contributions. (1) The Geometricity-Defect Theorem identifies quadratic covariation and coordinate covariance as the canonical failures of shuffle multiplicativity. (2) The Hopf Square proves that for pure-jump finite-variation paths, the forward Ito signature equals the iterated-sums signature, while the Marcus signature is Hoffman's exponential image of it. (3) Affine and exponential Hawkes processes are shown to admit finite-dimensional linear closures for truncated expected signatures after state-weight augmentation. For scalar Hawkes clocks, this allows explicit identification of baseline, excitation, and decay parameters. (4) An antisymmetric second-level cross-area is proved to detect two-channel Hawkes excitation direction to first order. Secondary results cover kernel-MMD decompositions, free nilpotent truncations, stable-law thresholds, heavy-tail normalizations, and a large-deviation principle. All identities and formulas are validated by a reproducibility script.
0
0
q-fin.MF 2026-06-29

Combined distress regions lift both value and survival

by Benjamin Avanzi, Bernard Wong +1 more

Balancing Shareholder Value and Financial Stability under a Reduced-Form Liquidation Model

A distress zone spanning both sides of the ruin threshold improves shareholder payouts and firm longevity simultaneously, unlike single-side

Figure from the paper full image
abstract click to expand
Modern resolution and prudential regimes increasingly wind up a distressed firm not at a single hard threshold but through a graduated, state-dependent process. We study how the design of such a regime shapes the trade-off between shareholder value and financial stability for a firm whose surplus follows a general diffusion. Forced liquidation is modelled in reduced form, arriving at a surplus-dependent hazard rate that rises as the firm's position deteriorates. The framework has three regions: an unregulated region where dividends may be paid, a regulated region where solvency requirements prohibit distributions, and a distress region in which the firm faces the liquidation hazard. To quantify shareholder value we solve the resulting singular stochastic control problem: which is to maximise the expected present value of distributions until liquidation. We establish a verification theorem, prove that a barrier strategy is optimal, and obtain tractable expressions for the value function and the expected survival time, so that alternative designs can be compared at low cost. We show that a distress region placed solely below or solely above the classical ruin threshold does not consistently improve both shareholder value and firm survival, whereas combining the two yields a Pareto improvement. Regulatory design is decisive.
0
0
q-fin.MF 2026-06-29

Electric aircraft cut emissions over 70% in five years on Canadian routes

by Elham Soufiani, Mehrdad Pirnia

Optimal Deployment of Electric Aircraft for Canadian Domestic Flights

Model finds fleet capacity and schedules, not charging stations, limit how quickly the switch can occur without leaving demand unmet.

Figure from the paper full image
abstract click to expand
This paper presents a multi-period mixed-integer linear programming (MILP) framework for planning the transition from conventional to electric aircraft in regional aviation. The model jointly optimizes fleet acquisition, infrastructure deployment, and service allocation over time, while accounting for policy constraints such as emissions reduction targets, electric service share, and budget limits. A real-world case study based on Helijet's short-haul network in British Columbia demonstrates the applicability of the model. The results show that electrification can reduce emissions by more than 70\% within five years while remaining economically viable. However, the transition is primarily limited by the capacity of the fleet and operational structure, rather than the charging infrastructure, leading to unmet demand under direct aircraft replacement. These findings emphasize the need for coordinated planning across fleet sizing, scheduling, and route prioritization to ensure a practical and efficient transition to electric aviation.
0
0
econ.GN 2026-06-29

Debiasing fixes ML bias in economic history with small expert samples

by Torben S. D. Johansen, Julius Koschnick +1 more

How to deal with machine learning bias in economic history

A modest random set of expert labels removes systematic prediction errors that otherwise distort historical estimates.

Figure from the paper full image
abstract click to expand
Machine learning (ML) has rapidly transformed economic history, lowering costs of digitization, data linkage, and imputation, and making information in historical text usable at scale. This paper offers a practical guide to using these tools well. However, ML tools have also created new problems. Prediction errors are often systematically correlated with covariates of interest, so even highly accurate models can distort and sometimes reverse coefficients, and standard validation cannot detect this. Given that ML tools often perform worse for historical data, this problem is especially severe for the field of economic history. We also identify a solution to this problem. We show that recent debiasing methods can correct such bias for a wide class of applications, using a small, randomly sampled set of expert-coded labels while retaining the efficiency of large-scale prediction. We organize the field with a taxonomy of three ML tasks, survey the literature along it, and indicate where debiasing applies and where validation against proxies remains the only recourse. We close with best-practice guidance on digitization, model choice, and reproducibility.
0
0
q-fin.ST 2026-06-29

Grünwald-Letnikov filter restores Hurst test under long memory

by Daniele Angelini

(In)Efficient Market States and Rough Volatility Detected via Grunwald-Letnikov Fractional Derivative

The method detects rough volatility and efficient versus persistent market states from single financial trajectories.

Figure from the paper full image
abstract click to expand
Testing self-similarity in fractional processes from a single observed trajectory is difficult under long-range dependence, because the associated Kolmogorov--Smirnov (KS) statistic undergoes a phase transition when $H>1/2$. In this regime, the classical limit collapses to a non-functional absolute Gaussian law and finite-sample convergence becomes severely distorted. This paper introduces a regime-adaptive KS/GL--KS framework based on the discrete Gr\"{u}nwald--Letnikov (GL) fractional derivative. The GL filter removes the low-frequency long-memory singularity while preserving the finite-dimensional $H$-self-similarity needed for distributional identification. We derive the filtered empirical-process limit, prove consistency and local asymptotic behavior of the resulting Hurst estimator, and validate the method through Monte Carlo simulations. Financial applications to realized volatility and equity index prices show how the procedure detects rough volatility and persistent, anti-persistent, or efficient market states.
0
0
econ.GN 2026-06-29

China EV subsidies return 3.38 yuan surplus per yuan spent

by Yu (Jasmine) Hao, Jinge Li

Heterogeneous Diffusion of Electric Vehicles in China: Demand, Learning, Product Entry, and the Incidence of Industrial Policy

Quality gains explain 45 percent of 2015-2024 share rise to 45 percent while learning effects drive half the welfare cost of removal.

Figure from the paper full image
abstract click to expand
China's electric-vehicle (EV) sales share rose from about 1% in 2015 to roughly 45% in 2024. We evaluate this technology transition with an equilibrium differentiated-products model of the Chinese auto market, and quantify both its attribution and its welfare and reallocation consequences. Every yuan of 2024 EV subsidy delivered about 3.38 yuan of private surplus, but this surplus accrued asymmetrically. Per-capita consumer-surplus loss from subsidy removal is about five times larger in Tier 1 than in the Rest tier; about half of the aggregate welfare loss operates through indirect Wright's-law learning rather than the direct cash transfer; and EV-native firms (BYD, Tesla, New Forces) retain 16-27% of their 2024 EV business under subsidy removal while traditional state-owned manufacturers retain only 11%. A Shapley decomposition into six channels -- Quality, Variety, Battery, Subsidy, Residual, and Market -- attributes the historical 2015-2024 rise primarily to product-quality gains (+45.49%), choice-set expansion (+14.81%), and battery-cost decline (+8.20%). The Subsidy block is negative (-13.63%) because direct purchase subsidies were phased down, not because subsidies reduce demand: a separate counterfactual that removes the 2024 subsidy entirely lowers EV share by 23-33%.
0
0
econ.GN 2026-06-29

LLMs retrieve fixed level-k strategies without belief updating

by Po Han Teo

LLM Agents as Static Level-k Players in Behavioural Games

In beauty contests and public goods games, model scale sets the level but no round-by-round adjustment or last-round defection occurs.

Figure from the paper full image
abstract click to expand
Large Language Models (LLMs) are increasingly used as stand-ins in behavioural games. These stand-ins rely on the assumption that the LLM's distribution of choices meaningfully matches how humans play the same game. This study tests that assumption through two games. The first is a p-beauty contest, and the second one is a public goods game. The study first investigates five local-model settings within the same model family. These settings are varied together in a 360-cell factorial, which balances temperature, scale (0.5-32B), quantisation, instruct vs base, and framing. Each cell's distribution is then compared against whole choice distributions in published human data. Each deployment setting, except for quantisation, governs a different aspect of fidelity. Mechanically, while the dispersion of human players can be somewhat recovered through deployment settings, the strategic process behind it cannot. Through the lens of the level-k cognitive theory, we find that LLMs act as static, category-retrieved level-k players, where k is set by the model scale. The models also do not run within-game belief-updating or backward induction throughout multiple-round horizon settings. While human contributions decayed in the public goods game, LLMs stayed flat or rose at every scale. When the horizon test was administered, LLMs were more cooperative under an indefinite horizon compared to a finite one. However, LLMs ignore their relative round position, so no last-round defection was displayed. This implies that LLMs retrieved levels relative to the horizon category rather than working out iteratively from the specific game setting.
0
0
q-fin.RM 2026-06-29

Review classifies 370 studies into five uncertainty method families

by Albert Kutej, Stefan Rass

Methods for Uncertainty Representation in Risk Management: A Comparative Review and Decision-Oriented Framework

Probabilistic approaches lead for rigor, but fuzzy and evidence methods handle vagueness better in risk decisions.

Figure from the paper full image
abstract click to expand
The consideration of uncertainty is a central but frequently inadequately addressed component of risk management. A systematic treatment of uncertainty is essential for ensuring the quality and traceability of decision-making processes, particularly in complex and safety-critical environments. This review systematically analyzes how established risk management approaches conceptualize and represent uncertainty in both their theoretical foundations and practical applications. Based on a systematic literature review of 370 publications, the identified approaches are classified into five methodological families. These include probabilistic methods, evidence-based and fuzzy-logic approaches, qualitative elicitation techniques, graphical and visual representations and hybrid frameworks. The analysis shows that probabilistic methods remain predominant due to their quantitative rigor, whereas fuzzy and evidence-based approaches are particularly suited to addressing vagueness and epistemic uncertainty. Qualitative and graphical approaches are found to enhance interpretive understanding and support the transparent communication of uncertainty. Despite these developments, the analysis indicates that the practical integration of these approaches into operational risk management remains limited in many domains. The findings highlight the need for more structured guidance in method selection and suggest that future research would benefit from further development of hybrid approaches and visualization techniques.
0
0
cs.CE 2026-06-29

Graph attention outperforms time series on crypto prices

by Yu Peng, Matloob Khushi +1 more

CryptoGAT: Are Time Series Models Effective for Cryptocurrency Forecasting?

By modeling cross-asset links as a graph instead of time sequences, it handles volatility that defeats standard temporal models.

Figure from the paper full image
abstract click to expand
Cryptocurrency price prediction is a significant challenge in quantitative investment. In recent years, time series models have made significant progress in financial forecasting tasks, especially in the stock market. Despite the growing performance over the past few years, we question the validity of this line of research in cryptocurrency prediction. Specifically, time series models (e.g., LSTM, GRU, and Transformers) are effective at extracting temporal relationships in stock market data. However, in pure price-based cryptocurrency prediction, facing data with extreme volatility and wild swings, time series models have difficulty learning effective information. To validate our claim, we propose CryptoGAT, a lightweight Graph Attention Network that recasts cryptocurrency pure price prediction as a cross-asset graph problem rather than a temporal modeling task. Extensive experiments on real cryptocurrency benchmarks demonstrate that our proposed CryptoGAT outperforms various state-of-the-art forecasting methods with a notable margin. Moreover, we conduct comprehensive empirical studies to explore the fundamental differences exposed by time series models in stock and cryptocurrency prediction: differences in predictability of the signal and cross-asset dependencies. This finding opens up new research directions for the cryptocurrency pure price prediction task and inspires further graph-based exploration in the field. The source code is available at https://github.com/FanBroWell/CryptoGAT
0
0
econ.GN 2026-06-26

REIT concentration links to 2.8 pp higher rent growth

by Advay Ranade

Measuring Racial Disparities in Rent Growth Under Algorithmic Landlord Concentration in U.S. Metros

Association reaches 5.9 points extra in majority-minority tracts across 665 census tracts after AHBI controls.

Figure from the paper full image
abstract click to expand
The 2024 Department of Justice antitrust complaint against RealPage, Inc. named five major residential REITs for coordinating algorithmic rent pricing across hundreds of thousands of apartment units in major US metropolitan areas. This paper studies whether census-tract-level corporate landlord concentration (CLC), measured from SEC EDGAR 10-K property filings geocoded to census tracts, the first such application in the literature, is associated with rent growth 2019-2023, and whether that association is larger in majority-minority neighborhoods. Rent outcomes are measured using the Zillow Observed Rent Index (ZORI). To account for the possibility that corporate landlords preferentially locate in neighborhoods already seeing rent appreciation, all regressions control for a fully novel Algorithmic Housing Burden Index (AHBI), a composite of pre-existing rent burden and market tightness from ACS data. Across 665 census tracts in ten US metropolitan areas, doubling REIT concentration is associated with 2.8 percentage points higher rent growth (p = 0.086, p = 0.030, HC1 robust). This association is significantly stronger in majority-minority tracts. Within the same metro, high-CLC majority-minority tracts are associated with 5.9 percentage points higher rent growth than comparable white tracts (p = 0.039). An XGBoost model predicts 44 percent of out-of-sample rent growth variance, with SHAP analysis independently confirming that CLC's contribution is positive in minority tracts and negative in white tracts. Taken all together, these findings provide the first tract-level evidence consistent with corporate landlord concentration being associated with disproportionately higher rent growth in communities of color.
0
0
stat.ML 2026-06-26

GMVP regret tracks only the weight-projected part of covariance error

by Xavier Fonseca

The Decision Geometry of Covariance Estimation for the Global Minimum-Variance Portfolio under Heavy Tails

An exact identity shows invariance to scale and (p-1) other directions, giving a sharper constant under heavy tails.

abstract click to expand
The global minimum-variance portfolio (GMVP) is the canonical decision built from an estimated covariance matrix, yet covariance estimators are universally evaluated by matrix-norm loss, which is not the object the decision depends on. We characterise exactly how covariance-estimation error maps into GMVP suboptimality. We prove an exact regret identity and a non-asymptotic bound showing decision regret depends on the estimation error only through its action on the portfolio weights, scaled by portfolio concentration and the conditioning of the true covariance. From this we derive the decision geometry: GMVP regret is invariant to a (p-1)-dimensional projection of the p^2-dimensional error matrix, with invariance to the covariance-scale direction as an exact special case. We then apply the framework to heavy-tailed returns (tail index kappa in (2,4)), establishing the regret convergence rate implied by the centred operator-norm rate, and confirm the theory on a skew-t/t-copula simulation design with pre-registered analysis. The decision-focused advantage is a sharper constant and a concentration discount rather than a faster rate; we report an honest high-conditioning boundary of the rate prediction. The results complement recent decision-focused learning approaches by supplying the exact estimation geometry and consistency theory they lack.
0
0
q-fin.CP 2026-06-26

Volterra equation prices American FX timing options

by Leif Andersen, Andrey Itkin +1 more

Valuing American options and Flexible Forwards contracts in time-dependent models

Spectral methods solve it in 1-2 seconds and reveal nonlinear variance dependence, outperforming finite differences by an order of magnitude

abstract click to expand
A flexible forward (FF) is a customized FX hedging instrument that guarantees a fixed exchange rate while letting the holder choose the delivery date within a pre-agreed window. It is therefore an American-style option on timing, and its valuation must respect the volatility skew of the underlying currency pair. We price FF contracts (and, more generally, American options) under a time-inhomogeneous Heston model which captures the forward-skew term structure while preserving analytical tractability through a recursive (matrix) Riccati solution for the joint characteristic function. Extending the integral-equation (decomposition) approach to time-dependent coefficients, we derive a Volterra equation characterizing the early-exercise surface. The expectation in the decomposition formula is evaluated by two complementary spectral methods: a double cosine (COS) expansion of the transition density, and a damped-Sinc (DSINC) local-basis scheme that is more accurate and stays robust when a low Feller ratio or large vol-of-vol induces Gibbs oscillations in the COS series. Benchmarked against a penalty-iteration MCS-ADI finite-difference solver, both methods price a contract in about 1-2 seconds, roughly an order of magnitude faster than the finest finite-difference grid, while DSINC improves median accuracy over COS by about a factor of twelve. The experiments also show that the early-exercise surface is a substantially nonlinear function of the variance, contrary to the linear-in-variance approximation common in earlier work.
0
0
q-fin.RM 2026-06-26

Threshold retention structure reduces reinsurance pricing to one dimension

by Ruimeng Hu, Byungdoo Kong

Endogenous Reinsurance Pricing in Large Competitive Insurance Markets: Finite-Player and Mean Field Analysis

Insurers move from full cession to partial retention to full retention as the premium rises, collapsing the reinsurer's problem to a compact

Figure from the paper full image
abstract click to expand
We study endogenous reinsurance pricing in a competitive insurance market with one strategic reinsurer and many heterogeneous insurers. The reinsurer acts as a Stackelberg leader by choosing a common premium rate and an investment strategy, while insurers decide how much risk to retain and how to invest, taking into account their own performance, their performance relative to the insurer population, and common insurance-claim and financial-market noise. This creates a feedback loop absent from standard reinsurance models with exogenous premiums: a premium change affects insurers directly through the cost of reinsurance, and indirectly through the population's aggregate exposure to common insurance-claim risk. For a fixed premium, we characterize the insurers' equilibrium retention through a scalar fixed point and establish its monotone premium response. This characterization reveals a spillover mechanism generated by relative performance concerns and leads to a threshold structure in which insurers move from full cession to partial retention and then to full retention as the premium increases. Using this structure, we reduce the reinsurer's premium problem to a one-dimensional optimization over a compact premium interval and characterize Stackelberg equilibria in both finite-player and mean field models. In the finite-player case, we develop an efficient threshold continuation procedure that determines equilibrium premiums without enumerating all retention configurations. We also prove convergence from finite-player equilibria to mean field equilibria without requiring the mean field equilibrium premium to be unique. Numerical illustrations show how relative performance concerns amplify spillover effects and can induce retention even when reinsurance remains actuarially favorable. They also demonstrate that Stackelberg equilibria need not be unique in either setting.
0
0
q-fin.MF 2026-06-26

Pretrained models top rankings but beat random walk in only 2 of 10 equity tasks

by Miquel Noguer i Alonso, Rodolfo Pereira Franklin

Pretrained Time-Series Foundation Models for Financial Return Forecasting

Tests on five U.S. stocks find foundation models reduce development cost yet deliver few statistically reliable gains over a naive benchmark

Figure from the paper full image
abstract click to expand
Financial return forecasting is a difficult test case for time-series foundation models (TSFMs) due to low signal-to-noise ratios, structural breaks, heavy tails, and weak persistence. This paper benchmarks pretrained TSFMs against train-from-scratch neural baselines in a deliberately conservative financial setting. We evaluate TimeGPT/TimeGPT-LH, TimesFM-2.5, Moirai-2.0, Chronos, and Chronos-2 against NBEATS, NHITS, PatchTST, iTransformer, and KAN on five liquid U.S. equities (AAPL, AMZN, GOOG, JPM, META) using linear and log returns. Models are compared under an equalized context budget, a rolling-origin protocol, and against random-walk benchmarks. We provide a theoretical framing of pretraining as an inductive prior, linking PAC-Bayes transfer intuition, information-theoretic predictability limits, and attention geometry. This clarifies why strong model rankings need not imply economically meaningful predictability in noisy markets. Pragmatically, pretrained TSFMs dominate the ranking distribution, accounting for 8 of 10 task-level wins. Moirai-2.0 and TimesFM-2.5 achieve the strongest average ranks, leading tasks for AAPL, JPM, GOOG, and AMZN, while Chronos wins the remaining AMZN task. However, the iTransformer baseline wins both META tasks, showing local supervised learning can still outperform generic pretraining for specific assets. Crucially, gains over the random-walk benchmark are small and sparse. A one-sided Diebold-Mariano test rejects equal or inferior predictive accuracy only for Chronos on AMZN and Moirai-2.0 on GOOG. We conclude that TSFMs serve as useful practical priors that reduce model-development costs in low-data financial forecasting, but are not universal engines for statistically reliable alpha generation in realistic empirical deployment.
0
0
stat.ME 2026-06-26

Recursive conditioning removes LR terms from Leibniz derivative estimator

by Xingyu Ren, Michael C. Fu +1 more

Conditional Leibniz Derivative Estimation with an Application to American Call Min-Options

The resulting estimator avoids dimension-dependent variance growth while remaining unbiased for discontinuous payoffs such as American call

Figure from the paper full image
abstract click to expand
Leibniz derivative estimation is a Monte Carlo technique for estimating derivatives of a discontinuous sample performance in stochastic models with respect to parameters of interest. By combining the push-out likelihood ratio (LR) method with Leibniz integral rules, it generalizes a broad class of existing LR-based derivative estimators. However, as an LR-based method, its variance is often higher than that of perturbation analysis-based methods and may grow linearly with the dimension of the stochastic input whose distribution depends on the parameter. In this paper, we propose a recursive conditioning approach and combine it with the Leibniz derivative estimation framework. The resulting conditional Leibniz estimator does not involve LR terms and therefore is not subject to variance growth with the input dimension. It also has a simple form and is easy to implement. We apply the method to an American call min-option model, and simulation results show its effectiveness and low-variance performance.
0
0
econ.GN 2026-06-26

Exogenous method yields consistent subnational complexity

by Wenli Du, Andrea Zaccaria

Economic complexity at subnational level: A consistency analysis

Product complexity estimates no longer vary with chosen geographical scale and track GDP per capita and employment more closely.

abstract click to expand
Several network-based measures have been proposed to assess the economic complexity of countries. These measures have provided important insights into national economic development, and they are now widely applied at the subnational level as well. Here, we show that such applications lead to inconsistent results, in the sense that the estimated complexity of the same product appears to depend on methodological details such as the geographical scale of analysis. Building on these findings, we propose a measure of territorial economic complexity based on an exogenous and extensive computation. We show that these methodological choices yield estimates that are more consistent and more strongly aligned with standard economic indicators, such as GDP per capita and employment.
0
0
econ.GN 2026-06-26

Codex data shows agentic AI users grew fivefold in six months

by Drew Johnston, David Holtz +4 more

The Shift to Agentic AI: Evidence from Codex

Request complexity rose nearly tenfold and output tokens increased up to 50 times for researchers inside OpenAI.

Figure from the paper full image
abstract click to expand
We analyze usage data from OpenAI's Codex tool to present large-scale evidence of how agentic AI technology, which can take actions on a user's behalf, changes how people work. We use an automated, privacy-protecting pipeline to contrast usage across three populations: external personal-account users, external organizational-account users, and workers within OpenAI. We find that agentic AI usage is growing rapidly: the number of active users has grown more than fivefold in the first half of 2026, with the most rapid increase occurring outside the initial audience of software developers. Uptake is uneven: within OpenAI, Codex usage is nearly universal and has largely replaced business usage of ChatGPT. We document a similar shift to agentic tooling outside OpenAI, particularly within organizations, although external adoption remains lower and more uneven. In addition to headline usage figures, we observe measures of sophistication, and find that a growing number of users have used Codex to change their workflows substantially. More than 10% of users manage three or more concurrent Codex agents at some point each week and that 26.6% use skills, which allow users to share instructions for complex workflows. Alongside these changes in usage practices, request complexity has increased: since the start of the year, the share of individual Codex users who submit at least one request for a task estimated to require more than eight hours for an experienced human to complete has increased nearly tenfold. Concurrently, output has grown rapidly -- in June 2026, the median OpenAI employee in a legal role generated 13 times more monthly output tokens across Codex and ChatGPT than they did in November 2025, while the median researcher generated more than 50 times as many. We conclude by discussing the implications of these patterns for productivity, job reorganization, and workforce restructuring.
0
0
q-fin.PM 2026-06-26

Price-of-risk attribution breaks at order three despite pairwise checks

by Alejandro Rodriguez Dominguez

A sharp order-three obstruction to the aggregation of conditional price-of-risk attribution

A decomposition into stable premium and causal wedge fails to aggregate across three drivers even when every pair is admissible.

Figure from the paper full image
abstract click to expand
We study the squared price-of-risk premium of a portfolio -- an integrated conditional squared Sharpe-ratio functional, not an expected excess return -- and its attribution to causal drivers. Relative to a declared admissible benchmark it decomposes into intervention-stable premium, a signed causal distortion (the confounding wedge), and a nonnegative information loss; the loss is an $L^2$ projection residual, the wedge is not. The decomposition is well posed exactly when the driver filtration is immersed in the price filtration. It need not aggregate across portfolios pooling drivers: we identify an order-three obstruction that is invisible to every singleton and pairwise admissibility screen -- each one- and two-driver sub-book is immersed while the pooled triple reveals a future innovation -- the analogue of Bernstein's pairwise-but-not-mutually-independent triple, and minimal relative to such pairwise diagnostics. We separate its two ingredients, combinatorial masking and anticipative coupling. The failure is one of immersion, not of no-arbitrage. Experiments on synthetic single- and multi-driver panels show the decomposition and its causal correction are estimable, and that a permutation-calibrated screen detects planted order-three leakage with controlled false positives.
0
0
q-fin.PM 2026-06-26

Neural networks outperform classical models in bond yield curve forecasts

by Tobias Lausser, Joao Eduardo Vuolo +1 more

Data-Driven Duration Management -- Term Structure Forecasting Using Machine Learning

Machine learning blends with factor models improve accuracy and trading returns for US and European government bonds.

Figure from the paper full image
abstract click to expand
This paper compares different methods for forecasting the term structure of U.S. and European zero-coupon government bonds using both traditional econometric and Machine Learning (ML) approaches. We compare classical models (e.g., Dynamic Nelson-Siegel (DNS) and Principal Component Analysis (PCA)) with different Neural Network (NN) architectures, including those inspired by the classical models, on the U.S. Treasury market and bonds issued by the European Central Bank (ECB). To enhance predictive performance, macroeconomic variables are incorporated. The findings for both markets are separately analyzed and compared. To this end, we propose a robust model evaluation framework combining statistical accuracy metrics - such as RMSE, MAE, and directional accuracy - with the economic relevance of a quantitative bond trading strategy. Results show that NNs consistently outperform traditional models in both forecasting accuracy and portfolio performance. For the U.S., the most effective approach is a direct-forecasting NN that incorporates DNS factors to reduce the dimensionality of zero-rate data and an Autoencoder (AE) to extract macroeconomic features, while for Europe, the optimal model is a factor-based NN using PCA-derived zero-rate factors without the integration of macroeconomic variables. Overall, the paper demonstrates how combining traditional modeling approaches with modern ML techniques and evaluation can improve yield curve forecasts and support applications in fixed-income portfolio construction.
0
0
q-fin.RM 2026-06-26

Wider no-trade bands cut rebalancing costs but raise hedge-error risk

by Takayuki Sakuma

Robust Hedging Valuation Adjustment under Liquidity--Demand Stress

Robust HVA computes worst-case expected loss inside relative-entropy neighborhoods of simulated loss distributions under liquidity-demand st

Figure from the paper full image
abstract click to expand
This paper develops a robust hedging valuation adjustment (HVA) measure for dynamic hedging. Simulated rebalancing and maturity-unwind trades generate a loss distribution for each no-trade-band rule, and we define robust HVA as the worst-case expected loss over a relative-entropy neighborhood of that distribution. Because band width affects turnover, the same relative-entropy radius applied to different bands can imply different levels of demand-liquidity stress. We distinguish a fixed-radius convention from a fixed benchmark-stress convention and show that wider no-trade bands lower rebalancing costs but raise hedge-error risk.
0
0
q-fin.PM 2026-06-26

CVaR optimization stabilizes commodity ETF portfolios

by Nicholas Appiah, Ali Jaffri +2 more

Portfolio Optimization for Commodity ETFs under Heavy-Tailed Returns

Minimum-risk and CVaR strategies outperform tangent portfolios on Sharpe and Calmar ratios for 30 ETFs, though tail risks persist.

Figure from the paper full image
abstract click to expand
This paper examines portfolio optimization for commodity exchange-traded funds (ETFs) under heavy-tailed return behavior. Using daily Bloomberg data for 30 U.S.-listed commodity ETFs from 12 December 2018 to 16 December 2024, we study funds spanning agriculture, energy, metals, and broad commodity index exposure. We compare a passive buy-and-hold portfolio with rolling-window optimized portfolios formed under mean--variance and conditional value-at-risk (CVaR) criteria, considering both long-only and restricted long--short strategies. The results showed substantial heterogeneity across commodity sectors, with energy and broad commodity index funds displaying pronounced volatility, skewness, and excess kurtosis. Historical optimization indicated that minimum-risk and CVaR-based portfolios provided more stable cumulative performance than tangent portfolios and generally improved Sharpe, Calmar, and STARR$_{0.95}$ ratios. Extreme-value diagnostics showed that optimized portfolios remained exposed to heavy downside tails, so improved risk-adjusted performance did not eliminate extreme-loss risk. A dynamic extension based on ARMA--GARCH marginal models, Student--$t$ copula dependence, and one-step-ahead predictive scenarios improved performance mainly when combined with minimum-risk or CVaR-based objectives. Dynamic mean--variance tangent portfolios performed less reliably, reflecting sensitivity to expected-return estimation error. Transaction-cost robustness checks further showed that the practical value of dynamic optimization depended on turnover control, with low-turnover dynamic CVaR tangent portfolios remaining more resilient to implementation costs. Overall, the analysis showed that commodity ETF allocation benefited most from conservative and downside-risk-aware optimization, while optimized portfolios continued to require explicit tail-risk and implementation diagnostics.
0
0
econ.GN 2026-06-26

Fusion cost models require over 30% learning rates to hit 110-144 USD/MWh

by Stefania Böhnlein, Fanny Böse +3 more

Too cheap to meter? A stochastic analysis of projected future fusion costs

Stochastic review of literature estimates finds mature MCF, ICF and MIF plants optimistic relative to fission benchmarks.

Figure from the paper full image
abstract click to expand
In recent years, technological developments and activities by private actors have led a reemerged discussion of the potential of nuclear fusion to meet growing global energy demands. So far, however, fusion technologies remain at comparatively low development levels and their deployment in commercial power plants is probably still decades away. Regardless, over the last decades, many cost studies have been conducted that estimate the future cost of potential fusion power plants. But to date, there is no systematic and harmonized assessment of these projections. Therefore, this study conducts a stochastic analysis of future fusion power plant costs for three distint technology lines, magnetic confinement, inertial confinement, and magneto-inertial confinement fusion, including cost assessments of different technology maturity levels. These levels are further assessed to determine projected learning rates for future fusion costs. For mature technologies, mean LCOE are determined at 114.6, 110.3, and 143.9 USD per MWh for MCF, ICF, and MIF devices, respectively. This implies learning rates of more than 30%. We find that these projected values are rather optimistic when compared to other literature or comparable technologies like fission. We therefore urge policymakers to caution when potential fusion developers refer to the potential economic competitiveness of fusion power plants.
0
0
econ.GN 2026-06-26

Chinese patents now cite more domestic science than U.S

by Ziyu Chen, Christopher Esposito

The Growing Self-Reliance of Chinese Innovation

Share of China-produced science behind Chinese patents rose from 1% in 2000 to 26% in 2025, overtaking the U.S. share in 2021.

abstract click to expand
U.S. policy increasingly seeks to slow China's technological rise by restricting its access to American science, on the assumption that Chinese innovation depends on U.S. science. Linking the full corpus of Chinese invention patents to the global scientific literature, we show that this dependence has fallen in recent years: the share of the China-produced science behind Chinese patents rose from 1% in 2000 to 26% in 2025, overtaking the U.S. share in 2021. As China's reliance on U.S.-produced science fades, policies restricting access fall out of alignment with the U.S.' actual strategic position.
0
0
q-fin.MF 2026-06-25

Return risk measures extend geometrically to AM-algebras

by Christian Laudagé

Geometrically convex return risk measures on AM-algebras

The move produces systemic and vector-valued versions with finiteness, continuity, and dual representations for multidimensional payoffs.

abstract click to expand
Monetary risk measures quantify the risk of uncertain monetary payoffs (or losses), whereas in time series analysis risk is typically assessed using logarithmic returns. Return risk measures (RRMs) provide an axiomatic foundation for this latter approach, which relies crucially on the positive cone of the space of essentially bounded random variables. We extend RRMs to general ordered vector spaces and characterize positive homogeneity via the geometric epigraph. To investigate geometric convexity and establish connections with monetary risk measures, we specialize the domain to AM-algebras, encompassing Euclidean spaces and spaces of multidimensional essentially bounded random variables. The latter is novel in the context of RRMs and leads to the new classes of systemic and vector-valued RRMs. We establish results on finiteness, continuity, separability, as well as dual and aggregation-based representations.
0

browse all of q-fin → full archive · search · sub-categories