FactorGCL: A Hypergraph-Based Factor Model with Temporal Residual Contrastive Learning for Stock Returns Prediction ArXiv ID: 2502.05218 “View on arXiv” Authors: Unknown Abstract As a fundamental method in economics and finance, the factor model has been extensively utilized in quantitative investment. In recent years, there has been a paradigm shift from traditional linear models with expert-designed factors to more flexible nonlinear machine learning-based models with data-driven factors, aiming to enhance the effectiveness of these factor models. However, due to the low signal-to-noise ratio in market data, mining effective factors in data-driven models remains challenging. In this work, we propose a hypergraph-based factor model with temporal residual contrastive learning (FactorGCL) that employs a hypergraph structure to better capture high-order nonlinear relationships among stock returns and factors. To mine hidden factors that supplement human-designed prior factors for predicting stock returns, we design a cascading residual hypergraph architecture, in which the hidden factors are extracted from the residual information after removing the influence of prior factors. Additionally, we propose a temporal residual contrastive learning method to guide the extraction of effective and comprehensive hidden factors by contrasting stock-specific residual information over different time periods. Our extensive experiments on real stock market data demonstrate that FactorGCL not only outperforms existing state-of-the-art methods but also mines effective hidden factors for predicting stock returns. ...

OrderFusion: Encoding Orderbook for End-to-End Probabilistic Intraday Electricity Price Forecasting ArXiv ID: 2502.06830 “View on arXiv” Authors: Unknown Abstract Probabilistic intraday electricity price forecasting is becoming increasingly important with the growth of renewable generation and the rise in demand-side engagement. Their uncertainties have increased the trading risks closer to delivery and the subsequent imbalance settlement costs. As a consequence, intraday trading has emerged to mitigate these risks. Unlike auction markets, intraday trading in many jurisdictions is characterized by the continuous posting of buy and sell orders on power exchange platforms. This dynamic orderbook microstructure of price formation presents special challenges for price forecasting. Conventional methods represent the orderbook via domain features aggregated from buy and sell trades, or by treating it as a multivariate time series, but such representations neglect the full buy-sell interaction structure of the orderbook. This research therefore develops a new order fusion methodology, which is an end-to-end and parameter-efficient probabilistic forecasting model that learns a full interaction-aware representation of the buy-sell dynamics. Furthermore, as quantile crossing is often a problem in probabilistic forecasting, this approach hierarchically estimates the quantiles with non-crossing constraints. Extensive experiments on the market price indices across high-liquidity (German) and low-liquidity (Austrian) markets demonstrate consistent improvements over conventional baselines, and ablation studies highlight the contributions of the main modeling components. The methodology is available at: https://runyao-yu.github.io/OrderFusion/. ...

FinBloom: Knowledge Grounding Large Language Model with Real-time Financial Data ArXiv ID: 2502.18471 “View on arXiv” Authors: Unknown Abstract Large language models (LLMs) excel at generating human-like responses but often struggle with interactive tasks that require access to real-time information. This limitation poses challenges in finance, where models must access up-to-date information, such as recent news or price movements, to support decision-making. To address this, we introduce Financial Agent, a knowledge-grounding approach for LLMs to handle financial queries using real-time text and tabular data. Our contributions are threefold: First, we develop a Financial Context Dataset of over 50,000 financial queries paired with the required context. Second, we train FinBloom 7B, a custom 7 billion parameter LLM, on 14 million financial news articles from Reuters and Deutsche Presse-Agentur, alongside 12 million Securities and Exchange Commission (SEC) filings. Third, we fine-tune FinBloom 7B using the Financial Context Dataset to serve as a Financial Agent. This agent generates relevant financial context, enabling efficient real-time data retrieval to answer user queries. By reducing latency and eliminating the need for users to manually provide accurate data, our approach significantly enhances the capability of LLMs to handle dynamic financial tasks. Our proposed approach makes real-time financial decisions, algorithmic trading and other related tasks streamlined, and is valuable in contexts with high-velocity data flows. ...

FinRLlama: A Solution to LLM-Engineered Signals Challenge at FinRL Contest 2024 ArXiv ID: 2502.01992 “View on arXiv” Authors: Unknown Abstract In response to Task II of the FinRL Challenge at ACM ICAIF 2024, this study proposes a novel prompt framework for fine-tuning large language models (LLM) with Reinforcement Learning from Market Feedback (RLMF). Our framework incorporates market-specific features and short-term price dynamics to generate more precise trading signals. Traditional LLMs, while competent in sentiment analysis, lack contextual alignment for financial market applications. To bridge this gap, we fine-tune the LLaMA-3.2-3B-Instruct model using a custom RLMF prompt design that integrates historical market data and reward-based feedback. Our evaluation shows that this RLMF-tuned framework outperforms baseline methods in signal consistency and achieving tighter trading outcomes; awarded as winner of Task II. You can find the code for this project on GitHub. ...

Liquidity provision of utility indifference type in decentralized exchanges ArXiv ID: 2502.01931 “View on arXiv” Authors: Unknown Abstract We present a mathematical formulation of liquidity provision in decentralized exchanges. We focus on constant function market makers of utility indifference type, which include constant product market makers with concentrated liquidity as a special case. First, we examine no-arbitrage conditions for a liquidity pool and compute an optimal arbitrage strategy when there is an external liquid market. Second, we show that liquidity provision suffers from impermanent loss unless a transaction fee is levied under the general framework with concentrated liquidity. Third, we establish the well-definedness of arbitrage-free reserve processes of a liquidity pool in continuous-time and show that there is no loss-versus-rebalancing under a nonzero fee if the external market price is continuous. We then argue that liquidity provision by multiple liquidity providers can be understood as liquidity provision by a representative liquidity provider, meaning that the analysis boils down to that for a single liquidity provider. Last, but not least, we give an answer to the fundamental question in which sense the very construction of constant function market makers with concentrated liquidity in the popular platform Uniswap v3 is optimal. ...

Regret-Optimized Portfolio Enhancement through Deep Reinforcement Learning and Future Looking Rewards ArXiv ID: 2502.02619 “View on arXiv” Authors: Unknown Abstract This paper introduces a novel agent-based approach for enhancing existing portfolio strategies using Proximal Policy Optimization (PPO). Rather than focusing solely on traditional portfolio construction, our approach aims to improve an already high-performing strategy through dynamic rebalancing driven by PPO and Oracle agents. Our target is to enhance the traditional 60/40 benchmark (60% stocks, 40% bonds) by employing the Regret-based Sharpe reward function. To address the impact of transaction fee frictions and prevent signal loss, we develop a transaction cost scheduler. We introduce a future-looking reward function and employ synthetic data training through a circular block bootstrap method to facilitate the learning of generalizable allocation strategies. We focus on two key evaluation measures: return and maximum drawdown. Given the high stochasticity of financial markets, we train 20 independent agents each period and evaluate their average performance against the benchmark. Our method not only enhances the performance of the existing portfolio strategy through strategic rebalancing but also demonstrates strong results compared to other baselines. ...

Theoretical Frameworks for Integrating Sustainability Factors into Institutional Investment Decision-Making ArXiv ID: 2502.13148 “View on arXiv” Authors: Unknown Abstract This paper explores key theoretical frameworks instrumental in understanding the relationship between sustainability and institutional investment decisions. The study identifies and analyzes various theories, including Behavioral Finance Theory, Modern Portfolio Theory, Risk Management Theory, and others, to explain how sustainability considerations increasingly influence investment choices. By examining these frameworks, the paper highlights how investors integrate Environmental, Social, and Governance (ESG) factors to optimize financial outcomes and align with broader societal goals. ...

When Dimensionality Hurts: The Role of LLM Embedding Compression for Noisy Regression Tasks ArXiv ID: 2502.02199 “View on arXiv” Authors: Unknown Abstract Large language models (LLMs) have shown remarkable success in language modelling due to scaling laws found in model size and the hidden dimension of the model’s text representation. Yet, we demonstrate that compressed representations of text can yield better performance in LLM-based regression tasks. In this paper, we compare the relative performance of embedding compression in three different signal-to-noise contexts: financial return prediction, writing quality assessment and review scoring. Our results show that compressing embeddings, in a minimally supervised manner using an autoencoder’s hidden representation, can mitigate overfitting and improve performance on noisy tasks, such as financial return prediction; but that compression reduces performance on tasks that have high causal dependencies between the input and target data. Our results suggest that the success of interpretable compressed representations such as sentiment may be due to a regularising effect. ...

An End-To-End LLM Enhanced Trading System ArXiv ID: 2502.01574 “View on arXiv” Authors: Unknown Abstract This project introduces an end-to-end trading system that leverages Large Language Models (LLMs) for real-time market sentiment analysis. By synthesizing data from financial news and social media, the system integrates sentiment-driven insights with technical indicators to generate actionable trading signals. FinGPT serves as the primary model for sentiment analysis, ensuring domain-specific accuracy, while Kubernetes is used for scalable and efficient deployment. ...

Regression and Forecasting of U.S. Stock Returns Based on LSTM ArXiv ID: 2502.05210 “View on arXiv” Authors: Unknown Abstract This paper analyses the investment returns of three stock sectors, Manuf, Hitec, and Other, in the U.S. stock market, based on the Fama-French three-factor model, the Carhart four-factor model, and the Fama-French five-factor model, in order to test the validity of the Fama-French three-factor model, the Carhart four-factor model, and the Fama-French five-factor model for the three sectors of the market. French five-factor model for the three sectors of the market. Also, the LSTM model is used to explore the additional factors affecting stock returns. The empirical results show that the Fama-French five-factor model has better validity for the three segments of the market under study, and the LSTM model has the ability to capture the factors affecting the returns of certain industries, and can better regress and predict the stock returns of the relevant industries. Keywords- Fama-French model; Carhart model; Factor model; LSTM model. ...