Machine learning approach to stock price crash risk ArXiv ID: 2505.16287 “View on arXiv” Authors: Abdullah Karasan, Ozge Sezgin Alp, Gerhard-Wilhelm Weber Abstract In this study, we propose a novel machine-learning-based measure for stock price crash risk, utilizing the minimum covariance determinant methodology. Employing this newly introduced dependent variable, we predict stock price crash risk through cross-sectional regression analysis. The findings confirm that the proposed method effectively captures stock price crash risk, with the model demonstrating strong performance in terms of both statistical significance and economic relevance. Furthermore, leveraging a newly developed firm-specific investor sentiment index, the analysis identifies a positive correlation between stock price crash risk and firm-specific investor sentiment. Specifically, higher levels of sentiment are associated with an increased likelihood of stock price crash risk. This relationship remains robust across different firm sizes and when using the detoned version of the firm-specific investor sentiment index, further validating the reliability of the proposed approach. ...

Towards Competent AI for Fundamental Analysis in Finance: A Benchmark Dataset and Evaluation ArXiv ID: 2506.07315 “View on arXiv” Authors: Zonghan Wu, Congyuan Zou, Junlin Wang, Chenhan Wang, Hangjing Yang, Yilei Shao Abstract Generative AI, particularly large language models (LLMs), is beginning to transform the financial industry by automating tasks and helping to make sense of complex financial information. One especially promising use case is the automatic creation of fundamental analysis reports, which are essential for making informed investment decisions, evaluating credit risks, guiding corporate mergers, etc. While LLMs attempt to generate these reports from a single prompt, the risks of inaccuracy are significant. Poor analysis can lead to misguided investments, regulatory issues, and loss of trust. Existing financial benchmarks mainly evaluate how well LLMs answer financial questions but do not reflect performance in real-world tasks like generating financial analysis reports. In this paper, we propose FinAR-Bench, a solid benchmark dataset focusing on financial statement analysis, a core competence of fundamental analysis. To make the evaluation more precise and reliable, we break this task into three measurable steps: extracting key information, calculating financial indicators, and applying logical reasoning. This structured approach allows us to objectively assess how well LLMs perform each step of the process. Our findings offer a clear understanding of LLMs current strengths and limitations in fundamental analysis and provide a more practical way to benchmark their performance in real-world financial settings. ...

Agent-based Liquidity Risk Modelling for Financial Markets ArXiv ID: 2505.15296 “View on arXiv” Authors: Perukrishnen Vytelingum, Rory Baggott, Namid Stillman, Jianfei Zhang, Dingqiu Zhu, Tao Chen, Justin Lyon Abstract In this paper, we describe a novel agent-based approach for modelling the transaction cost of buying or selling an asset in financial markets, e.g., to liquidate a large position as a result of a margin call to meet financial obligations. The simple act of buying or selling in the market causes a price impact and there is a cost described as liquidity risk. For example, when selling a large order, there is market slippage – each successive trade will execute at the same or worse price. When the market adjusts to the new information revealed by the execution of such a large order, we observe in the data a permanent price impact that can be attributed to the change in the fundamental value as market participants reassess the value of the asset. In our ABM model, we introduce a novel mechanism where traders assume orderflow is informed and each trade reveals some information about the value of the asset, and traders update their belief of the fundamental value for every trade. The result is emergent, realistic price impact without oversimplifying the problem as most stylised models do, but within a realistic framework that models the exchange with its protocols, its limit orderbook and its auction mechanism and that can calculate the transaction cost of any execution strategy without limitation. Our stochastic ABM model calculates the costs and uncertainties of buying and selling in a market by running Monte-Carlo simulations, for a better understanding of liquidity risk and can be used to optimise for optimal execution under liquidity risk. We demonstrate its practical application in the real world by calculating the liquidity risk for the Hang-Seng Futures Index. ...

Deep Learning for Continuous-time Stochastic Control with Jumps ArXiv ID: 2505.15602 “View on arXiv” Authors: Patrick Cheridito, Jean-Loup Dupret, Donatien Hainaut Abstract In this paper, we introduce a model-based deep-learning approach to solve finite-horizon continuous-time stochastic control problems with jumps. We iteratively train two neural networks: one to represent the optimal policy and the other to approximate the value function. Leveraging a continuous-time version of the dynamic programming principle, we derive two different training objectives based on the Hamilton-Jacobi-Bellman equation, ensuring that the networks capture the underlying stochastic dynamics. Empirical evaluations on different problems illustrate the accuracy and scalability of our approach, demonstrating its effectiveness in solving complex, high-dimensional stochastic control tasks. ...

Quantile Predictions for Equity Premium using Penalized Quantile Regression with Consistent Variable Selection across Multiple Quantiles ArXiv ID: 2505.16019 “View on arXiv” Authors: Shaobo Li, Ben Sherwood Abstract This paper considers equity premium prediction, for which mean regression can be problematic due to heteroscedasticity and heavy-tails of the error. We show advantages of quantile predictions using a novel penalized quantile regression that offers a model for a full spectrum analysis on the equity premium distribution. To enhance model interpretability and address the well-known issue of crossing quantile predictions in quantile regression, we propose a model that enforces the selection of a common set of variables across all quantiles. Such a selection consistency is achieved by simultaneously estimating all quantiles with a group penalty that ensures sparsity pattern is the same for all quantiles. Consistency results are provided that allow the number of predictors to increase with the sample size. A Huberized quantile loss function and an augmented data approach are implemented for computational efficiency. Simulation studies show the effectiveness of the proposed approach. Empirical results show that the proposed method outperforms several benchmark methods. Moreover, we find some important predictors reverse their relationship to the excess return from lower to upper quantiles, potentially offering interesting insights to the domain experts. Our proposed method can be applied to other fields. ...

R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization ArXiv ID: 2505.15155 “View on arXiv” Authors: Yuante Li, Xu Yang, Xiao Yang, Minrui Xu, Xisen Wang, Weiqing Liu, Jiang Bian Abstract Financial markets pose fundamental challenges for asset return prediction due to their high dimensionality, non-stationarity, and persistent volatility. Despite advances in large language models and multi-agent systems, current quantitative research pipelines suffer from limited automation, weak interpretability, and fragmented coordination across key components such as factor mining and model innovation. In this paper, we propose R&D-Agent for Quantitative Finance, in short RD-Agent(Q), the first data-centric multi-agent framework designed to automate the full-stack research and development of quantitative strategies via coordinated factor-model co-optimization. RD-Agent(Q) decomposes the quant process into two iterative stages: a Research stage that dynamically sets goal-aligned prompts, formulates hypotheses based on domain priors, and maps them to concrete tasks, and a Development stage that employs a code-generation agent, Co-STEER, to implement task-specific code, which is then executed in real-market backtests. The two stages are connected through a feedback stage that thoroughly evaluates experimental outcomes and informs subsequent iterations, with a multi-armed bandit scheduler for adaptive direction selection. Empirically, RD-Agent(Q) achieves up to 2X higher annualized returns than classical factor libraries using 70% fewer factors, and outperforms state-of-the-art deep time-series models on real markets. Its joint factor-model optimization delivers a strong balance between predictive accuracy and strategy robustness. Our code is available at: https://github.com/microsoft/RD-Agent. ...

Shortermism and excessive risk taking in optimal execution with a target performance ArXiv ID: 2505.15611 “View on arXiv” Authors: Emilio Barucci, Yuheng Lan Abstract We deal with the optimal execution problem when the broker’s goal is to reach a performance barrier avoiding a downside barrier. The performance is provided by the wealth accumulated by trading in the market, the shares detained by the broker evaluated at the market price plus a slippage cost yielding a quadratic inventory cost. Over a short horizon, this type of remuneration leads, at the same time, to a more aggressive and less risky strategy compared to the classical one, and over a long horizon the performance turns to be poorer and more dispersed. ...

Cryptocurrencies in the Balance Sheet: Insights from (Micro)Strategy – Bitcoin Interactions ArXiv ID: 2505.14655 “View on arXiv” Authors: Sabrina Aufiero, Antonio Briola, Tesfaye Salarin, Fabio Caccioli, Silvia Bartolucci, Tomaso Aste Abstract This paper investigates the evolving link between cryptocurrency and equity markets in the context of the recent wave of corporate Bitcoin (BTC) treasury strategies. We assemble a dataset of 39 publicly listed firms holding BTC, from their first acquisition through April 2025. Using daily logarithmic returns, we first document significant positive co-movements via Pearson correlations and single factor model regressions, discovering an average BTC beta of 0.62, and isolating 12 companies, including Strategy (formerly MicroStrategy, MSTR), exhibiting a beta exceeding 1. We then classify firms into three groups reflecting their exposure to BTC, liquidity, and return co-movements. We use transfer entropy (TE) to capture the direction of information flow over time. Transfer entropy analysis consistently identifies BTC as the dominant information driver, with brief, announcement-driven feedback from stocks to BTC during major financial events. Our results highlight the critical need for dynamic hedging ratios that adapt to shifting information flows. These findings provide important insights for investors and managers regarding risk management and portfolio diversification in a period of growing integration of digital assets into corporate treasuries. ...

Quantum Reservoir Computing for Realized Volatility Forecasting ArXiv ID: 2505.13933 “View on arXiv” Authors: Qingyu Li, Chiranjib Mukhopadhyay, Abolfazl Bayat, Ali Habibnia Abstract Recent advances in quantum computing have demonstrated its potential to significantly enhance the analysis and forecasting of complex classical data. Among these, quantum reservoir computing has emerged as a particularly powerful approach, combining quantum computation with machine learning for modeling nonlinear temporal dependencies in high-dimensional time series. As with many data-driven disciplines, quantitative finance and econometrics can hugely benefit from emerging quantum technologies. In this work, we investigate the application of quantum reservoir computing for realized volatility forecasting. Our model employs a fully connected transverse-field Ising Hamiltonian as the reservoir with distinct input and memory qubits to capture temporal dependencies. The quantum reservoir computing approach is benchmarked against several econometric models and standard machine learning algorithms. The models are evaluated using multiple error metrics and the model confidence set procedures. To enhance interpretability and mitigate current quantum hardware limitations, we utilize wrapper-based forward selection for feature selection, identifying optimal subsets, and quantifying feature importance via Shapley values. Our results indicate that the proposed quantum reservoir approach consistently outperforms benchmark models across various metrics, highlighting its potential for financial forecasting despite existing quantum hardware constraints. This work serves as a proof-of-concept for the applicability of quantum computing in econometrics and financial analysis, paving the way for further research into quantum-enhanced predictive modeling as quantum hardware capabilities continue to advance. ...

SAE-FiRE: Enhancing Earnings Surprise Predictions Through Sparse Autoencoder Feature Selection ArXiv ID: 2505.14420 “View on arXiv” Authors: Huopu Zhang, Yanguang Liu, Miao Zhang, Zirui He, Mengnan Du Abstract Predicting earnings surprises from financial documents, such as earnings conference calls, regulatory filings, and financial news, has become increasingly important in financial economics. However, these financial documents present significant analytical challenges, typically containing over 5,000 words with substantial redundancy and industry-specific terminology that creates obstacles for language models. In this work, we propose the SAE-FiRE (Sparse Autoencoder for Financial Representation Enhancement) framework to address these limitations by extracting key information while eliminating redundancy. SAE-FiRE employs Sparse Autoencoders (SAEs) to decompose dense neural representations from large language models into interpretable sparse components, then applies statistical feature selection methods, including ANOVA F-tests and tree-based importance scoring, to identify the top-k most discriminative dimensions for classification. By systematically filtering out noise that might otherwise lead to overfitting, we enable more robust and generalizable predictions. Experimental results across three financial datasets demonstrate that SAE-FiRE significantly outperforms baseline approaches. ...