Equities

A Test of Lookahead Bias in LLM Forecasts ArXiv ID: 2512.23847 “View on arXiv” Authors: Zhenyu Gao, Wenxi Jiang, Yutong Yan Abstract We develop a statistical test to detect lookahead bias in economic forecasts generated by large language models (LLMs). Using state-of-the-art pre-training data detection techniques, we estimate the likelihood that a given prompt appeared in an LLM’s training corpus, a statistic we term Lookahead Propensity (LAP). We formally show that a positive correlation between LAP and forecast accuracy indicates the presence and magnitude of lookahead bias, and apply the test to two forecasting tasks: news headlines predicting stock returns and earnings call transcripts predicting capital expenditures. Our test provides a cost-efficient, diagnostic tool for assessing the validity and reliability of LLM-generated forecasts. ...

Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning ArXiv ID: 2512.23515 “View on arXiv” Authors: Zuoyou Jiang, Li Zhao, Rui Sun, Ruohan Sun, Zhongjian Li, Jing Li, Daxin Jiang, Zuo Bai, Cheng Hua Abstract Signal decay and regime shifts pose recurring challenges for data-driven investment strategies in non-stationary markets. Conventional time-series and machine learning approaches, which rely primarily on historical correlations, often struggle to generalize when the economic environment changes. While large language models (LLMs) offer strong capabilities for processing unstructured information, their potential to support quantitative factor screening through explicit economic reasoning remains underexplored. Existing factor-based methods typically reduce alphas to numerical time series, overlooking the semantic rationale that determines when a factor is economically relevant. We propose Alpha-R1, an 8B-parameter reasoning model trained via reinforcement learning for context-aware alpha screening. Alpha-R1 reasons over factor logic and real-time news to evaluate alpha relevance under changing market conditions, selectively activating or deactivating factors based on contextual consistency. Empirical results across multiple asset pools show that Alpha-R1 consistently outperforms benchmark strategies and exhibits improved robustness to alpha decay. The full implementation and resources are available at https://github.com/FinStep-AI/Alpha-R1. ...

Broken Symmetry of Stock Returns – a Modified Jones-Faddy Skew t-Distribution ArXiv ID: 2512.23640 “View on arXiv” Authors: Siqi Shao, Arshia Ghasemi, Hamed Farahani, R. A. Serota Abstract We argue that negative skew and positive mean of the distribution of stock returns are largely due to the broken symmetry of stochastic volatility governing gains and losses. Starting with stochastic differential equations for stock returns and for stochastic volatility we argue that the distribution of stock returns can be effectively split in two – for gains and losses – assuming difference in parameters of their respective stochastic volatilities. A modified Jones-Faddy skew t-distribution utilized here allows to reflect this in a single organic distribution which tends to meaningfully capture this asymmetry. We illustrate its application on distribution of daily S&P500 returns, including analysis of its tails. ...

Beyond Binary Screens: A Continuous Shariah Compliance Index for Asset Pricing and Portfolio Design ArXiv ID: 2512.22858 “View on arXiv” Authors: Abdulrahman Qadi, Akash Sharma, Francesca Medda Abstract Binary Shariah screens vary across standards and apply hard thresholds that create discontinuous classifications. We construct a Continuous Shariah Compliance Index (CSCI) in $[“0,1”]$ by mapping standard screening ratios to smooth scores between conservative ``comfort’’ bounds and permissive outer bounds, and aggregating them conservatively with a sectoral activity factor. Using CRSP/Compustat U.S. equities (1999-2024) with lagged accounting inputs and monthly rebalancing, we find that CSCI-based long-only portfolios have historical risk-adjusted performance similar to an emulated binary Islamic benchmark. Tightening the minimum compliance threshold reduces the investable universe and diversification and is associated with lower Sharpe ratios. The framework yields a practical compliance gradient that supports portfolio construction, constraint design, and cross-standard comparisons without reliance on pass/fail screening. ...

Squeezed Covariance Matrix Estimation: Analytic Eigenvalue Control ArXiv ID: 2512.23021 “View on arXiv” Authors: Layla Abu Khalaf, William Smyth Abstract We revisit Gerber’s Informational Quality (IQ) framework, a data-driven approach for constructing correlation matrices from co-movement evidence, and address two obstacles that limit its use in portfolio optimization: guaranteeing positive semidefinite ness (PSD) and controlling spectral conditioning. We introduce a squeezing identity that represents IQ estimators as a convex-like combination of structured channel matrices, and propose an atomic-IQ parameterization in which each channel-class matrix is built from PSD atoms with a single class-level normalization. This yields constructive PSD guarantees over an explicit feasibility region, avoiding reliance on ex-post projection. To regulate conditioning, we develop an analytic eigen floor that targets either a minimum eigenvalue or a desired condition number and, when necessary, repairs PSD violations in closed form while remaining compatible with the squeezing identity. In long-only tangency back tests with transaction costs, atomic-IQ improves out-of-sample Sharpe ratios and delivers a more stable risk profile relative to a broad set of standard covariance estimators. ...

Needles in a haystack: using forensic network science to uncover insider trading ArXiv ID: 2512.18918 “View on arXiv” Authors: Gian Jaeger, Wang Ngai Yeung, Renaud Lambiotte Abstract Although the automation and digitisation of anti-financial crime investigation has made significant progress in recent years, detecting insider trading remains a unique challenge, partly due to the limited availability of labelled data. To address this challenge, we propose using a data-driven networks approach that flags groups of corporate insiders who report coordinated transactions that are indicative of insider trading. Specifically, we leverage data on 2.9 million trades reported to the U.S. Securities and Exchange Commission (SEC) by company insiders (C-suite executives, board members and major shareholders) between 2014 and 2024. Our proposed algorithm constructs weighted edges between insiders based on the temporal similarity of their trades over the 10-year timeframe. Within this network we then uncover trends that indicate insider trading by focusing on central nodes and anomalous subgraphs. To highlight the validity of our approach we evaluate our findings with reference to two null models, generated by running our algorithm on synthetic empirically calibrated and shuffled datasets. The results indicate that our approach can be used to detect pairs or clusters of insiders whose behaviour suggests insider trading and/or market manipulation. ...

Extending the application of dynamic Bayesian networks in calculating market risk: Standard and stressed expected shortfall ArXiv ID: 2512.12334 “View on arXiv” Authors: Eden Gross, Ryan Kruger, Francois Toerien Abstract In the last five years, expected shortfall (ES) and stressed ES (SES) have become key required regulatory measures of market risk in the banking sector, especially following events such as the global financial crisis. Thus, finding ways to optimize their estimation is of great importance. We extend the application of dynamic Bayesian networks (DBNs) to the estimation of 10-day 97.5% ES and stressed ES, building on prior work applying DBNs to value at risk. Using the S&P 500 index as a proxy for the equities trading desk of a US bank, we compare the performance of three DBN structure-learning algorithms with several traditional market risk models, using either the normal or the skewed Student’s t return distributions. Backtesting shows that all models fail to produce statistically accurate ES and SES forecasts at the 2.5% level, reflecting the difficulty of modeling extreme tail behavior. For ES, the EGARCH(1,1) model (normal) produces the most accurate forecasts, while, for SES, the GARCH(1,1) model (normal) performs best. All distribution-dependent models deteriorate substantially when using the skewed Student’s t distribution. The DBNs perform comparably to the historical simulation model, but their contribution to tail prediction is limited by the small weight assigned to their one-day-ahead forecasts within the return distribution. Future research should examine weighting schemes that enhance the influence of forward-looking DBN forecasts on tail risk estimation. ...

Local and Global Balance in Financial Correlation Networks: an Application to Investment Decisions ArXiv ID: 2512.10606 “View on arXiv” Authors: Paolo Bartesaghi, Rosanna Grassi, Pierpaolo Uberti Abstract The global balance is a well-known indicator of the behavior of a signed network. Recent literature has introduced the concept of local balance as a measure of the contribution of a single node to the overall balance of the network. In the present research, we investigate the potential of using deviations of local balance from global balance as a criterion for selecting outperforming assets. The underlying idea is that, during financial crises, most assets in the investment universe behave similarly: losses are severe and widespread, and the global balance of the correlation-based signed network reaches its maximum value. Under such circumstances, standard diversification (mainly related to portfolio size) is unable to reduce risk or limit losses. Therefore, it may be useful to concentrate portfolio exposures on the few assets - if such assets exist-that behave differently from the rest of the market. We argue that these assets are those for which the local balance strongly departs from the global balance of the underlying signed network. The paper supports this hypothesis through an application using real financial data. The results, in both descriptive and predictive contexts, confirm the proposed intuition. ...

Not All Factors Crowd Equally: Modeling, Measuring, and Trading on Alpha Decay ArXiv ID: 2512.11913 “View on arXiv” Authors: Chorok Lee Abstract We derive a specific functional form for factor alpha decay – hyperbolic decay alpha(t) = K/(1+lambda*t) – from a game-theoretic equilibrium model, and test it against linear and exponential alternatives. Using eight Fama-French factors (1963–2024), we find: (1) Hyperbolic decay fits mechanical factors. Momentum exhibits clear hyperbolic decay (R^2 = 0.65), outperforming linear (0.51) and exponential (0.61) baselines – validating the equilibrium foundation. (2) Not all factors crowd equally. Mechanical factors (momentum, reversal) fit the model; judgment-based factors (value, quality) do not – consistent with a signal-ambiguity taxonomy paralleling Hua and Sun’s “barriers to entry.” (3) Crowding accelerated post-2015. Out-of-sample, the model over-predicts remaining alpha (0.30 vs. 0.15), correlating with factor ETF growth (rho = -0.63). (4) Average returns are efficiently priced. Crowding-based factor selection fails to generate alpha (Sharpe: 0.22 vs. 0.39 factor momentum benchmark). (5) Crowding predicts tail risk. Out-of-sample (2001–2024), crowded reversal factors show 1.7–1.8x higher crash probability (bottom decile returns), while crowded momentum shows lower crash risk (0.38x, p = 0.006). Our findings extend equilibrium crowding models (DeMiguel et al.) to temporal dynamics and show that crowding predicts crashes, not means – useful for risk management, not alpha generation. ...

Exploratory Mean-Variance with Jumps: An Equilibrium Approach ArXiv ID: 2512.09224 “View on arXiv” Authors: Yuling Max Chen, Bin Li, David Saunders Abstract Revisiting the continuous-time Mean-Variance (MV) Portfolio Optimization problem, we model the market dynamics with a jump-diffusion process and apply Reinforcement Learning (RL) techniques to facilitate informed exploration within the control space. We recognize the time-inconsistency of the MV problem and adopt the time-inconsistent control (TIC) approach to analytically solve for an exploratory equilibrium investment policy, which is a Gaussian distribution centered on the equilibrium control of the classical MV problem. Our approach accounts for time-inconsistent preferences and actions, and our equilibrium policy is the best option an investor can take at any given time during the investment period. Moreover, we leverage the martingale properties of the equilibrium policy, design a RL model, and propose an Actor-Critic RL algorithm. All of our RL model parameters converge to the corresponding true values in a simulation study. Our numerical study on 24 years of real market data shows that the proposed RL model is profitable in 13 out of 14 tests, demonstrating its practical applicability in real world investment. ...