arXiv · arXiv · 2026
ESG-aware portfolio optimization is increasingly important for sustainable capital allocation, yet most learning-based methods still operationalize ESG by appending static scores to the policy observation or reward. This creates a mismatch for sequential control: ESG scores are noisy, provider-dependent, low-frequency, and temporally misaligned with sequential portfolio decisions, while financial evidence suggests th…
Xin Li, Yan Ke, Longbing Cao
arXiv · arXiv · 2024
Credit scores are critical for allocating consumer debt in the United States, yet little evidence is available on their performance. We benchmark a widely used credit score against a machine learning model of consumer default and find significant misclassification of borrowers, especially those with low scores. Our model improves predictive accuracy for young, low-income, and minority groups due to its superior perfo…
Stefania Albanesi, Domonkos F. Vamossy
arXiv · arXiv · 2023
Neural SDEs are continuous-time generative models for sequential data. State-of-the-art performance for irregular time series generation has been previously obtained by training these models adversarially as GANs. However, as typical for GAN architectures, training is notoriously unstable, often suffers from mode collapse, and requires specialised techniques such as weight clipping and gradient penalty to mitigate th…
Zacharia Issa, Blanka Horvath, Maud Lemercier, Cristopher Salvi
arXiv · arXiv q-fin · 2025
As decentralized finance (DeFi) evolves, distinguishing between user behaviors - liquidity provision versus active trading - has become vital for risk modeling and on-chain reputation. We propose a behavioral scoring framework for Uniswap that assigns two complementary scores: a Liquidity Provision Score that assesses strategic liquidity contributions, and a Swap Behavior Score that reflects trading intent, volatilit…
Dhanashekar Kandaswamy, Ashutosh Sahoo, Akshay SP, Gurukiran S, Parag Paul
arXiv · arXiv · 2026
Bankruptcy is a low-frequency but high-impact corporate event, making early risk identification important for creditors, investors, regulators, and risk managers. Traditional bankruptcy-prediction models rely primarily on accounting ratios, but these measures may reflect financial deterioration only after it appears in reported financial statements. Narrative disclosures in annual 10-K filings may therefore provide i…
Zhen Zhang, Moxuan Zheng, Tongchen Zhang, Luyun Lin, Yiqing Wang
arXiv · arXiv q-fin · 2025
In this work we propose a framework to construct Market-Implied Sustainability (MIS) scores for individual firms by exploiting fund-level sustainability classifications and granular portfolio holdings. The central idea is that the relative over/under-representation of a stock in sustainability-oriented funds reveals a market-based assessment of its sustainability profile. We implement the methodology in the European …
Rosella Giacometti, Gabriele Torri, Marco Bonomelli, Davide Lauria
arXiv · arXiv · 2024
This research presents a comprehensive framework for analyzing liquidity in financial markets, particularly in the context of high-frequency trading. By leveraging advanced machine learning classification techniques, including Logistic Regression, Support Vector Machine, and Random Forest, the study aims to predict minute-level price movements using an extensive set of liquidity metrics derived from the Trade and Quo…
Sid Bhatia, Sidharth Peri, Sam Friedman, Michelle Malen
arXiv · arXiv · 2023
This paper investigates the application of Deep Reinforcement Learning (DRL) for Environment, Social, and Governance (ESG) financial portfolio management, with a specific focus on the potential benefits of ESG score-based market regulation. We leveraged an Advantage Actor-Critic (A2C) agent and conducted our experiments using environments encoded within the OpenAI Gym, adapted from the FinRL platform. The study inclu…
Eduardo C. Garrido-Merchán, Sol Mora-Figueroa-Cruz-Guzmán, María Coronado-Vaca
arXiv · arXiv q-fin · 2010
We review different approaches for measuring the impact of liquidity on CDS prices. We start with reduced form models incorporating liquidity as an additional discount rate. We review Chen, Fabozzi and Sverdlove (2008) and Buhler and Trapp (2006, 2008), adopting different assumptions on how liquidity rates enter the CDS premium rate formula, about the dynamics of liquidity rate processes and about the credit-liquidit…
Damiano Brigo, Mirela Predescu, Agostino Capponi
arXiv · arXiv · 2026
Modern portfolio management increasingly demands a balance between traditional risk-adjusted returns and strict Environmental, Social, and Governance (ESG) mandates. Current Reinforcement Learning (RL) approaches typically optimize for a single ESG provider, neglecting the significant divergence in rating methodologies across the industry and the unintuitive nature of manually weighting conflicting objectives. This p…
Giovanni Dispoto, Marcello Restelli, Carmine Ventre
arXiv · arXiv · 2026
Market stress rarely harms investors through one channel alone. Losses, volatility spikes, and deteriorating tradability often arrive together. We examine whether ESG is associated with lower exposure to clustered fragility in equity markets. Using monthly data on S&P 500 constituents from 2014 to 2025, we study downside returns, volatility, illiquidity, and a cofragility state that captures their joint occurrence wi…
Minxuan Hu, Jiayu Yi, Ziheng Chen, Wenxi Sun, Qishi Zhan
arXiv · arXiv · 2025
Multi-strategy hedge funds face a fundamental organizational choice: should analysts generating trading strategies communicate, and if so, how? We investigate this using 5-agent LLM-based trading systems across 450 experiments spanning 21 months, comparing five organizational structures from isolated baseline to collaborative and competitive conversation. We show that communication improves performance, but optimal c…
Jerick Shi, Burton Hollifield
arXiv · arXiv · 2025
Large language models (LLMs) achieve strong performance across benchmarks--from knowledge quizzes and math reasoning to web-agent tasks--but these tests occur in static settings, lacking real dynamics and uncertainty. Consequently, they evaluate isolated reasoning or problem-solving rather than decision-making under uncertainty. To address this, we introduce LiveTradeBench, a live trading environment for evaluating L…
Haofei Yu, Fenghai Li, Jiaxuan You
arXiv · arXiv · 2025
I identify a new signaling channel in ESG research by empirically examining whether environmental, social, and governance (ESG) investing remains valuable as large institutional investors increasingly shift toward artificial intelligence (AI). Using winsorized ESG scores of S&P 500 firms from Yahoo Finance and controlling for market value of equity, I conduct cross-sectional regressions to test the signaling mechanis…
Qionghua Chu
arXiv · arXiv · 2025
Price Trend Prediction (PTP) based on Limit Order Book (LOB) data is a fundamental challenge in financial markets. Despite advances in deep learning, existing models fail to generalize across different market conditions and assets. Surprisingly, by adapting a simple MLP-based architecture to LOB, we show that we surpass SoTA performance; thus, challenging the necessity of complex architectures. Unlike past work that …
Leonardo Berti, Gjergji Kasneci
arXiv · arXiv · 2024
We investigate the efficacy of large language models (LLMs) in sentiment analysis of U.S. financial news and their potential in predicting stock market returns. We analyze a dataset comprising 965,375 news articles that span from January 1, 2010, to June 30, 2023; we focus on the performance of various LLMs, including BERT, OPT, FINBERT, and the traditional Loughran-McDonald dictionary model, which has been a dominan…
Kemal Kirtac, Guido Germano
arXiv · arXiv · 2024
I explore the relationship between investor emotions expressed on social media and asset prices. The field has seen a proliferation of models aimed at extracting firm-level sentiment from social media data, though the behavior of these models often remains uncertain. Against this backdrop, my study employs EmTract, an open-source emotion model, to test whether the emotional responses identified on social media platfo…
Domonkos F. Vamossy
arXiv · arXiv · 2024
This paper conducts an extensive analysis of Bitcoin return series, with a primary focus on three volatility metrics: historical volatility (calculated as the sample standard deviation), forecasted volatility (derived from GARCH-type models), and implied volatility (computed from the emerging Bitcoin options market). These measures of volatility serve as indicators of market expectations for conditional volatility an…
Cristina Chinazzo, Vahidin Jeleskovic