Extracting the Structure of Press Releases for Predicting Earnings Announcement Returns ArXiv ID: 2509.24254 “View on arXiv” Authors: Yuntao Wu, Ege Mert Akin, Charles Martineau, Vincent Grégoire, Andreas Veneris Abstract We examine how textual features in earnings press releases predict stock returns on earnings announcement days. Using over 138,000 press releases from 2005 to 2023, we compare traditional bag-of-words and BERT-based embeddings. We find that press release content (soft information) is as informative as earnings surprise (hard information), with FinBERT yielding the highest predictive power. Combining models enhances explanatory strength and interpretability of the content of press releases. Stock prices fully reflect the content of press releases at market open. If press releases are leaked, it offers predictive advantage. Topic analysis reveals self-serving bias in managerial narratives. Our framework supports real-time return prediction through the integration of online learning, provides interpretability and reveals the nuanced role of language in price formation. ...

From Headlines to Holdings: Deep Learning for Smarter Portfolio Decisions ArXiv ID: 2509.24144 “View on arXiv” Authors: Yun Lin, Jiawei Lou, Jinghe Zhang Abstract Deep learning offers new tools for portfolio optimization. We present an end-to-end framework that directly learns portfolio weights by combining Long Short-Term Memory (LSTM) networks to model temporal patterns, Graph Attention Networks (GAT) to capture evolving inter-stock relationships, and sentiment analysis of financial news to reflect market psychology. Unlike prior approaches, our model unifies these elements in a single pipeline that produces daily allocations. It avoids the traditional two-step process of forecasting asset returns and then applying mean–variance optimization (MVO), a sequence that can introduce instability. We evaluate the framework on nine U.S. stocks spanning six sectors, chosen to balance sector diversity and news coverage. In this setting, the model delivers higher cumulative returns and Sharpe ratios than equal-weighted and CAPM-based MVO benchmarks. Although the stock universe is limited, the results underscore the value of integrating price, relational, and sentiment signals for portfolio management and suggest promising directions for scaling the approach to larger, more diverse asset sets. ...

Noise estimation of SDE from a single data trajectory ArXiv ID: 2509.25484 “View on arXiv” Authors: Munawar Ali, Purba Das, Qi Feng, Liyao Gao, Guang Lin Abstract In this paper, we propose a data-driven framework for model discovery of stochastic differential equations (SDEs) from a single trajectory, without requiring the ergodicity or stationary assumption on the underlying continuous process. By combining (stochastic) Taylor expansions with Girsanov transformations, and using the drift function’s initial value as input, we construct drift estimators while simultaneously recovering the model noise. This allows us to recover the underlying $\mathbb P$ Brownian motion increments. Building on these estimators, we introduce the first stochastic Sparse Identification of Stochastic Differential Equation (SSISDE) algorithm, capable of identifying the governing SDE dynamics from a single observed trajectory without requiring ergodicity or stationarity. To validate the proposed approach, we conduct numerical experiments with both linear and quadratic drift-diffusion functions. Among these, the Black-Scholes SDE is included as a representative case of a system that does not satisfy ergodicity or stationarity. ...

STRAPSim: A Portfolio Similarity Metric for ETF Alignment and Portfolio Trades ArXiv ID: 2509.24151 “View on arXiv” Authors: Mingshu Li, Dhruv Desai, Jerinsh Jeyapaulraj, Philip Sommer, Riya Jain, Peter Chu, Dhagash Mehta Abstract Accurately measuring portfolio similarity is critical for a wide range of financial applications, including Exchange-traded Fund (ETF) recommendation, portfolio trading, and risk alignment. Existing similarity measures often rely on exact asset overlap or static distance metrics, which fail to capture similarities among the constituents (e.g., securities within the portfolio) as well as nuanced relationships between partially overlapping portfolios with heterogeneous weights. We introduce STRAPSim (Semantic, Two-level, Residual-Aware Portfolio Similarity), a novel method that computes portfolio similarity by matching constituents based on semantic similarity, weighting them according to their portfolio share, and aggregating results via residual-aware greedy alignment. We benchmark our approach against Jaccard, weighted Jaccard, as well as BERTScore-inspired variants across public classification, regression, and recommendation tasks, as well as on corporate bond ETF datasets. Empirical results show that our method consistently outperforms baselines in predictive accuracy and ranking alignment, achieving the highest Spearman correlation with return-based similarity. By leveraging constituent-aware matching and dynamic reweighting, portfolio similarity offers a scalable, interpretable framework for comparing structured asset baskets, demonstrating its utility in ETF benchmarking, portfolio construction, and systematic execution. ...

Rethinking Portfolio Risk: Forecasting Volatility Through Cointegrated Asset Dynamics ArXiv ID: 2509.23533 “View on arXiv” Authors: Gabriele Casto Abstract We introduce the Historical and Dynamic Volatility Ratios (HVR/DVR) and show that equity and index volatilities are cointegrated at intraday and daily horizons. This allows us to construct a VECM to forecast portfolio volatility by exploiting volatility cointegration. On S&P 500 data, HVR is generally stationary and cointegration with the index is frequent; the VECM implementation yields substantially lower mean absolute percentage error (MAPE) than covariance-based forecasts at short- to medium-term horizons across portfolio sizes. The approach is interpretable and readily implementable, factorizing covariance into market volatility, relative-volatility ratios, and correlations. ...

SIMPOL Model for Solving Continuous-Time Heterogeneous Agent Problems ArXiv ID: 2509.23557 “View on arXiv” Authors: Ricardo Alonzo Fernández Salguero Abstract This paper presents SIMPOL (Simplified Policy Iteration), a modular numerical framework for solving continuous-time heterogeneous agent models. The core economic problem, the optimization of consumption and savings under idiosyncratic uncertainty, is formulated as a coupled system of partial differential equations: a Hamilton-Jacobi-Bellman (HJB) equation for the agent’s optimal policy and a Fokker-Planck-Kolmogorov (FPK) equation for the stationary wealth distribution. SIMPOL addresses this system using Howard’s policy iteration with an upwind finite difference scheme that guarantees stability. A distinctive contribution is a novel consumption policy post-processing module that imposes regularity through smoothing and a projection onto an economically plausible slope band, improving convergence and model behavior. The robustness and accuracy of SIMPOL are validated through a set of integrated diagnostics, including verification of contraction in the Wasserstein-2 metric and comparison with the analytical solution of the Merton model in the no-volatility case. The framework is shown to be not only computationally efficient but also to produce solutions consistent with economic and mathematical theory, offering a reliable tool for research in quantitative macroeconomics. ...

Conditional Risk Minimization with Side Information: A Tractable, Universal Optimal Transport Framework ArXiv ID: 2509.23128 “View on arXiv” Authors: Xinqiao Xie, Jonathan Yu-Meng Li Abstract Conditional risk minimization arises in high-stakes decisions where risk must be assessed in light of side information, such as stressed economic conditions, specific customer profiles, or other contextual covariates. Constructing reliable conditional distributions from limited data is notoriously difficult, motivating a series of optimal-transport-based proposals that address this uncertainty in a distributionally robust manner. Yet these approaches remain fragmented, each constrained by its own limitations: some rely on point estimates or restrictive structural assumptions, others apply only to narrow classes of risk measures, and their structural connections are unclear. We introduce a universal framework for distributionally robust conditional risk minimization, built on a novel union-ball formulation in optimal transport. This framework offers three key advantages: interpretability, by subsuming existing methods as special cases and revealing their deep structural links; tractability, by yielding convex reformulations for virtually all major risk functionals studied in the literature; and scalability, by supporting cutting-plane algorithms for large-scale conditional risk problems. Applications to portfolio optimization with rank-dependent expected utility highlight the practical effectiveness of the framework, with conditional models converging to optimal solutions where unconditional ones clearly do not. ...

Investor Sentiment and Market Movements: A Granger Causality Perspective ArXiv ID: 2510.15915 “View on arXiv” Authors: Tamoghna Mukherjee Abstract The stock market is heavily influenced by investor sentiment, which can drive buying or selling behavior. Sentiment analysis helps in gauging the overall sentiment of market participants towards a particular stock or the market as a whole. Positive sentiment often leads to increased buying activity and vice versa. Granger causality can be applied to ascertain whether changes in sentiment precede changes in stock prices.The study is focused on this aspect and tries to understand the relationship between close price index and sentiment score with the help of Granger causality inference. The study finds a positive response through hypothesis testing. ...

Factor-Based Conditional Diffusion Model for Portfolio Optimization ArXiv ID: 2509.22088 “View on arXiv” Authors: Xuefeng Gao, Mengying He, Xuedong He Abstract We propose a novel conditional diffusion model for portfolio optimization that learns the cross-sectional distribution of next-day stock returns conditioned on asset-specific factors. The model builds on the Diffusion Transformer with token-wise conditioning, linking each asset’s return to its own factor vector while capturing cross-asset dependencies. Generated return samples are used for daily mean-variance optimization under realistic constraints. Empirical results on the Chinese A-share market show that our approach consistently outperforms benchmark methods based on standard empirical and shrinkage-based estimators across multiple metrics. ...

Forecasting Liquidity Withdraw with Machine Learning Models ArXiv ID: 2509.22985 “View on arXiv” Authors: Haochuan, Wang Abstract Liquidity withdrawal is a critical indicator of market fragility. In this project, I test a framework for forecasting liquidity withdrawal at the individual-stock level, ranging from less liquid stocks to highly liquid large-cap tickers, and evaluate the relative performance of competing model classes in predicting short-horizon order book stress. We introduce the Liquidity Withdrawal Index (LWI) – defined as the ratio of order cancellations to the sum of standing depth and new additions at the best quotes – as a bounded, interpretable measure of transient liquidity removal. Using Nasdaq market-by-order (MBO) data, we compare a spectrum of approaches: linear benchmarks (AR, HAR), and non-linear tree ensembles (XGBoost), across horizons ranging from 250,ms to 5,s. Beyond predictive accuracy, our results provide insights into order placement and cancellation dynamics, identify regimes where linear versus non-linear signals dominate, and highlight how early-warning indicators of liquidity withdrawal can inform both market surveillance and execution. ...