Multi-asset optimal trade execution with stochastic cross-effects: An Obizhaeva-Wang-type framework ArXiv ID: 2503.05594 “View on arXiv” Authors: Unknown Abstract We analyze a continuous-time optimal trade execution problem in multiple assets where the price impact and the resilience can be matrix-valued stochastic processes that incorporate cross-impact effects. In addition, we allow for stochastic terminal and running targets. Initially, we formulate the optimal trade execution task as a stochastic control problem with a finite-variation control process that acts as an integrator both in the state dynamics and in the cost functional. We then extend this problem continuously to a stochastic control problem with progressively measurable controls. By identifying this extended problem as equivalent to a certain linear-quadratic stochastic control problem, we can use established results in linear-quadratic stochastic control to solve the extended problem. This work generalizes [“Ackermann, Kruse, Urusov; FinancStoch'24”] from the single-asset setting to the multi-asset case. In particular, we reveal cross-hedging effects, showing that it can be optimal to trade in an asset despite having no initial position. Moreover, as a subsetting we discuss a multi-asset variant of the model in [“Obizhaeva, Wang; JFinancMark'13”]. ...

Towards Temporal-Aware Multi-Modal Retrieval Augmented Generation in Finance ArXiv ID: 2503.05185 “View on arXiv” Authors: Unknown Abstract Finance decision-making often relies on in-depth data analysis across various data sources, including financial tables, news articles, stock prices, etc. In this work, we introduce FinTMMBench, the first comprehensive benchmark for evaluating temporal-aware multi-modal Retrieval-Augmented Generation (RAG) systems in finance. Built from heterologous data of NASDAQ 100 companies, FinTMMBench offers three significant advantages. 1) Multi-modal Corpus: It encompasses a hybrid of financial tables, news articles, daily stock prices, and visual technical charts as the corpus. 2) Temporal-aware Questions: Each question requires the retrieval and interpretation of its relevant data over a specific time period, including daily, weekly, monthly, quarterly, and annual periods. 3) Diverse Financial Analysis Tasks: The questions involve 10 different financial analysis tasks designed by domain experts, including information extraction, trend analysis, sentiment analysis and event detection, etc. We further propose a novel TMMHybridRAG method, which first leverages LLMs to convert data from other modalities (e.g., tabular, visual and time-series data) into textual format and then incorporates temporal information in each node when constructing graphs and dense indexes. Its effectiveness has been validated in extensive experiments, but notable gaps remain, highlighting the challenges presented by our FinTMMBench. ...

Are Large Language Models Good In-context Learners for Financial Sentiment Analysis? ArXiv ID: 2503.04873 “View on arXiv” Authors: Unknown Abstract Recently, large language models (LLMs) with hundreds of billions of parameters have demonstrated the emergent ability, surpassing traditional methods in various domains even without fine-tuning over domain-specific data. However, when it comes to financial sentiment analysis (FSA)$\unicode{“x2013”}$a fundamental task in financial AI$\unicode{“x2013”}$these models often encounter various challenges, such as complex financial terminology, subjective human emotions, and ambiguous inclination expressions. In this paper, we aim to answer the fundamental question: whether LLMs are good in-context learners for FSA? Unveiling this question can yield informative insights on whether LLMs can learn to address the challenges by generalizing in-context demonstrations of financial document-sentiment pairs to the sentiment analysis of new documents, given that finetuning these models on finance-specific data is difficult, if not impossible at all. To the best of our knowledge, this is the first paper exploring in-context learning for FSA that covers most modern LLMs (recently released DeepSeek V3 included) and multiple in-context sample selection methods. Comprehensive experiments validate the in-context learning capability of LLMs for FSA. ...

CoFinDiff: Controllable Financial Diffusion Model for Time Series Generation ArXiv ID: 2503.04164 “View on arXiv” Authors: Unknown Abstract The generation of synthetic financial data is a critical technology in the financial domain, addressing challenges posed by limited data availability. Traditionally, statistical models have been employed to generate synthetic data. However, these models fail to capture the stylized facts commonly observed in financial data, limiting their practical applicability. Recently, machine learning models have been introduced to address the limitations of statistical models; however, controlling synthetic data generation remains challenging. We propose CoFinDiff (Controllable Financial Diffusion model), a synthetic financial data generation model based on conditional diffusion models that accept conditions about the synthetic time series. By incorporating conditions derived from price data into the conditional diffusion model via cross-attention, CoFinDiff learns the relationships between the conditions and the data, generating synthetic data that align with arbitrary conditions. Experimental results demonstrate that: (i) synthetic data generated by CoFinDiff capture stylized facts; (ii) the generated data accurately meet specified conditions for trends and volatility; (iii) the diversity of the generated data surpasses that of the baseline models; and (iv) models trained on CoFinDiff-generated data achieve improved performance in deep hedging task. ...

Fredholm Approach to Nonlinear Propagator Models ArXiv ID: 2503.04323 “View on arXiv” Authors: Unknown Abstract We formulate and solve an optimal trading problem with alpha signals, where transactions induce a nonlinear transient price impact described by a general propagator model, including power-law decay. Using a variational approach, we demonstrate that the optimal trading strategy satisfies a nonlinear stochastic Fredholm equation with both forward and backward coefficients. We prove the existence and uniqueness of the solution under a monotonicity condition reflecting the nonlinearity of the price impact. Moreover, we derive an existence result for the optimal strategy beyond this condition when the underlying probability space is countable. In addition, we introduce a novel iterative scheme and establish its convergence to the optimal trading strategy. Finally, we provide a numerical implementation of the scheme that illustrates its convergence, stability, and the effects of concavity on optimal execution strategies under exponential and power-law decay. ...

Hedging with Sparse Reward Reinforcement Learning ArXiv ID: 2503.04218 “View on arXiv” Authors: Unknown Abstract Derivatives, as a critical class of financial instruments, isolate and trade the price attributes of risk assets such as stocks, commodities, and indices, aiding risk management and enhancing market efficiency. However, traditional hedging models, constrained by assumptions such as continuous trading and zero transaction costs, fail to satisfy risk control requirements in complex and uncertain real-world markets. With advances in computing technology and deep learning, data-driven trading strategies are becoming increasingly prevalent. This thesis proposes a derivatives hedging framework integrating deep learning and reinforcement learning. The framework comprises a probabilistic forecasting model and a hedging agent, enabling market probability prediction, derivative pricing, and hedging. Specifically, we design a spatiotemporal attention-based probabilistic financial time series forecasting Transformer to address the scarcity of derivatives hedging data. A low-rank attention mechanism compresses high-dimensional assets into a low-dimensional latent space, capturing nonlinear asset relationships. The Transformer models sequential dependencies within this latent space, improving market probability forecasts and constructing an online training environment for downstream hedging tasks. Additionally, we incorporate generalized geometric Brownian motion to develop a risk-neutral pricing approach for derivatives. We model derivatives hedging as a reinforcement learning problem with sparse rewards and propose a behavior cloning-based recurrent proximal policy optimization (BC-RPPO) algorithm. This pretraining-finetuning framework significantly enhances the hedging agent’s performance. Numerical experiments in the U.S. and Chinese financial markets demonstrate our method’s superiority over traditional approaches. ...

Matrix H-theory approach to stock market fluctuations ArXiv ID: 2503.08697 “View on arXiv” Authors: Unknown Abstract We introduce matrix H theory, a framework for analyzing collective behavior arising from multivariate stochastic processes with hierarchical structure. The theory models the joint distribution of the multiple variables (the measured signal) as a compound of a large-scale multivariate distribution with the distribution of a slowly fluctuating background. The background is characterized by a hierarchical stochastic evolution of internal degrees of freedom, representing the correlations between stocks at different time scales. As in its univariate version, the matrix H-theory formalism also has two universality classes: Wishart and inverse Wishart, enabling a concise description of both the background and the signal probability distributions in terms of Meijer G-functions with matrix argument. Empirical analysis of daily returns of stocks within the S&P500 demonstrates the effectiveness of matrix H theory in describing fluctuations in stock markets. These findings contribute to a deeper understanding of multivariate hierarchical processes and offer potential for developing more informed portfolio strategies in financial markets. ...

Risk-aware Trading Portfolio Optimization ArXiv ID: 2503.04662 “View on arXiv” Authors: Unknown Abstract We investigate portfolio optimization in financial markets from a trading and risk management perspective. We term this task Risk-Aware Trading Portfolio Optimization (RATPO), formulate the corresponding optimization problem, and propose an efficient Risk-Aware Trading Swarm (RATS) algorithm to solve it. The key elements of RATPO are a generic initial portfolio P, a specific set of Unique Eligible Instruments (UEIs), their combination into an Eligible Optimization Strategy (EOS), an objective function, and a set of constraints. RATS searches for an optimal EOS that, added to P, improves the objective function repecting the constraints. RATS is a specialized Particle Swarm Optimization method that leverages the parameterization of P in terms of UEIs, enables parallel computation with a large number of particles, and is fully general with respect to specific choices of the key elements, which can be customized to encode financial knowledge and needs of traders and risk managers. We showcase two RATPO applications involving a real trading portfolio made of hundreds of different financial instruments, an objective function combining both market risk (VaR) and profit&loss measures, constrains on market sensitivities and UEIs trading costs. In the case of small-sized EOS, RATS successfully identifies the optimal solution and demonstrates robustness with respect to hyper-parameters tuning. In the case of large-sized EOS, RATS markedly improves the portfolio objective value, optimizing risk and capital charge while respecting risk limits and preserving expected profits. Our work bridges the gap between the implementation of effective trading strategies and compliance with stringent regulatory and economic capital requirements, allowing a better alignment of business and risk management objectives. ...

Wasserstein Robust Market Making via Entropy Regularization ArXiv ID: 2503.04072 “View on arXiv” Authors: Unknown Abstract In this paper, we introduce a robust market making framework based on Wasserstein distance, utilizing a stochastic policy approach enhanced by entropy regularization. We demonstrate that, under mild assumptions, the robust market making problem can be reformulated as a convex optimization question. Additionally, we outline a methodology for selecting the optimal radius of the Wasserstein ball, further refining our framework’s effectiveness. ...

Large language models in finance : what is financial sentiment? ArXiv ID: 2503.03612 “View on arXiv” Authors: Unknown Abstract Financial sentiment has become a crucial yet complex concept in finance, increasingly used in market forecasting and investment strategies. Despite its growing importance, there remains a need to define and understand what financial sentiment truly represents and how it can be effectively measured. We explore the nature of financial sentiment and investigate how large language models (LLMs) contribute to its estimation. We trace the evolution of sentiment measurement in finance, from market-based and lexicon-based methods to advanced natural language processing techniques. The emergence of LLMs has significantly enhanced sentiment analysis, providing deeper contextual understanding and greater accuracy in extracting sentiment from financial text. We examine how BERT-based models, such as RoBERTa and FinBERT, are optimized for structured sentiment classification, while GPT-based models, including GPT-4, OPT, and LLaMA, excel in financial text generation and real-time sentiment interpretation. A comparative analysis of bidirectional and autoregressive transformer architectures highlights their respective roles in investor sentiment analysis, algorithmic trading, and financial decision-making. By exploring what financial sentiment is and how it is estimated within LLMs, we provide insights into the growing role of AI-driven sentiment analysis in finance. ...