|
on Financial Markets |
| By: | Jian Xue; Qian Zhang; Wu Zhu |
| Abstract: | We study how generative artificial intelligence (AI) transforms the work of financial analysts. Using the 2023 launch of FactSet's AI platform as a natural experiment, we find that adoption produces markedly richer and more comprehensive reports -- featuring 40% more distinct information sources, 34% broader topical coverage, and 25% greater use of advanced analytical methods -- while also improving timeliness. However, forecast errors rise by 59% as AI-assisted reports convey a more balanced mix of positive and negative information that is harder to synthesize, particularly for analysts facing heavier cognitive demands. Placebo tests using other data vendors confirm that these effects are unique to FactSet's AI integration. Overall, our findings reveal both the productivity gains and cognitive limits of generative AI in financial information production. |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2512.19705 |
| By: | Sandeep Neela |
| Abstract: | Financial crises emerge when structural vulnerabilities accumulate across sectors, markets, and investor behavior. Predicting these systemic transitions is challenging because they arise from evolving interactions between market participants, not isolated price movements alone. We present Systemic Risk Radar (SRR), a framework that models financial markets as multi-layer graphs to detect early signs of systemic fragility and crash-regime transitions. We evaluate SRR across three major crises: the Dot-com crash, the Global Financial Crisis, and the COVID-19 shock. Our experiments compare snapshot GNNs, a simplified temporal GNN prototype, and standard baselines (logistic regression and Random Forest). Results show that structural network information provides useful early-warning signals compared to feature-based models alone. This correlation-based instantiation of SRR demonstrates that graph-derived features capture meaningful changes in market structure during stress events. The findings motivate extending SRR with additional graph layers (sector/factor exposure, sentiment) and more expressive temporal architectures (LSTM/GRU or Transformer encoders) to better handle diverse crisis types. |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2512.17185 |
| By: | Gang Li; Dandan Qiao; Mingxuan Zheng |
| Abstract: | We find that event features extracted by large language models (LLMs) are effective for text-based stock return prediction. Using a pre-trained LLM to extract event features from news articles, we propose a novel deep learning model based on structured event representation (SER) and attention mechanisms to predict stock returns in the cross-section. Our SER-based model provides superior performance compared with other existing text-driven models to forecast stock returns out of sample and offers highly interpretable feature structures to examine the mechanisms underlying the stock return predictability. We further provide various implications based on SER and highlight the crucial benefit of structured model inputs in stock return predictability. |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2512.19484 |
| By: | Ming Gu; David Hirshleifer; Siew Hong Teoh; Shijia Wu |
| Abstract: | We study dynamic visual representations as a proxy for investor sentiment about the stock market. Our sentiment index, GIFsentiment, is constructed from millions of posts in the Graphics Interchange Format (GIF) on a leading investment social media platform. GIFsentiment correlates with seasonal mood variations and the severity of COVID lockdowns. It is positively associated with contemporaneous market returns and negatively predicts returns for up to four weeks, even after controlling for other sentiment and attention measures. These effects are stronger among portfolios that are more susceptible to mispricing. GIFsentiment positively predicts trading volume, market volatility, and flows toward equity funds and away from debt funds. Our evidence suggests that GIFsentiment is a proxy for misperceptions that are later corrected. |
| JEL: | C53 D84 D85 D91 G12 G14 G4 G41 |
| Date: | 2026–01 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:34636 |
| By: | Anastasiia Zbandut |
| Abstract: | This paper measures price differences between Hegic option quotes on Arbitrum and a model-based benchmark built on Black--Scholes model with regime-sensitive volatility estimated via a two-regime MS-AR-(GJR)-GARCH model. Using option-level feasible GLS, we find benchmark prices exceed Hegic quotes on average, especially for call options. The price spread rises with order size, strike, maturity, and estimated volatility, and falls with trading volume. By underlying, wrapped Bitcoin options show larger and more persistent spreads, while Ethereum options are closer to the benchmark. The framework offers a data-driven analysis for monitoring and calibrating on-chain option pricing logic. |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2512.20190 |
| By: | Travon Lucius; Christian Koch Jr; Jacob Starling; Julia Zhu; Miguel Urena; Carrie Hu |
| Abstract: | We present a reinforcement-learning (RL) framework for dynamic hedging of equity index option exposures under realistic transaction costs and position limits. We hedge a normalized option-implied equity exposure (one unit of underlying delta, offset via SPY) by trading the underlying index ETF, using the option surface and macro variables only as state information and not as a direct pricing engine. Building on the "deep hedging" paradigm of Buehler et al. (2019), we design a leak-free environment, a cost-aware reward function, and a lightweight stochastic actor-critic agent trained on daily end-of-day panel data constructed from SPX/SPY implied volatility term structure, skew, realized volatility, and macro rate context. On a fixed train/validation/test split, the learned policy improves risk-adjusted performance versus no-hedge, momentum, and volatility-targeting baselines (higher point-estimate Sharpe); only the GAE policy's test-sample Sharpe is statistically distinguishable from zero, although confidence intervals overlap with a long-SPY benchmark so we stop short of claiming formal dominance. Turnover remains controlled and the policy is robust to doubled transaction costs. The modular codebase, comprising a data pipeline, simulator, and training scripts, is engineered for extensibility to multi-asset overlays, alternative objectives (e.g., drawdown or CVaR), and intraday data. From a portfolio management perspective, the learned overlay is designed to sit on top of an existing SPX or SPY allocation, improving the portfolio's mean-variance trade-off with controlled turnover and drawdowns. We discuss practical implications for portfolio overlays and outline avenues for future work. |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2512.12420 |
| By: | Suparna Biswas; Rituparna Sen |
| Abstract: | Historically, financial risk management has mostly addressed risk factors that arise from the financial environment. Climate risks present a novel and significant challenge for companies and financial markets. Investors aiming for avoidance of firms with high carbon footprints require suitable risk measures and portfolio management strategies. This paper presents the construction of decarbonized indices for tracking the S \& P-500 index of the U.S. stock market, as well as the Indian index NIFTY-50, employing two distinct methodologies and study their performances. These decarbonized indices optimize the portfolio weights by minimizing the mean-VaR and mean-ES and seek to reduce the risk of significant financial losses while still pursuing decarbonization goals. Investors can thereby find a balance between financial performance and environmental responsibilities. Ensuring transparency in the development of these indices will encourage the excluded and under-weighted asset companies to lower their carbon footprints through appropriate action plans. For long-term passive investors, these indices may present a more favourable option than green stocks. |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2512.21092 |
| By: | Roudari, Soheil; Ahmadian- Yazdi, Farzaneh; Chenarani, Hasan; Mensi, Walid |
| Abstract: | Middle Eastern countries, due to their natural and financial resources, occupy a strategic position in the global economy. Despite this, portfolio management of their financial markets remains largely unexplored amid political and geopolitical crises. This study investigates return spillovers among eight selected currencies, analyzing total connectedness (TCI), net transmitters and receivers of risk, dynamic optimal weights, hedge effectiveness, cumulative returns, and Sharpe ratios using MVP, MCP, and MCOP approaches. Findings based on Broadstock et al. (2022) approach, show that the UAE and Saudi Arabia currencies are the main risk transmitters, while Lebanon is the primary receiver. The Israeli shekel exhibits the lowest network connection, making it a suitable asset for portfolio diversification. TCI surged to 65% during the Russia-Ukraine war, reducing diversification opportunities, then rose again during the Israel-Hamas conflict and the 12-day Israel-Iran war, ultimately reaching 50% by the study’s end. Optimal weights and hedge effectiveness indicate that currency selection depends on market conditions and the applied approach; for example, the Qatari stock market offers significant risk management potential, while the MCP approach achieves the highest cumulative returns and Sharpe ratios. Overall, the study highlights that effective risk management in the Middle East requires attention to geopolitical dynamics and structural market changes, providing practical insights for investors and policymakers to optimize asset allocation and enhance financial stability in high-risk environments. |
| Keywords: | Risk spillovers, Portfolio management, Geopolitical risk, Middle East Stock Markets |
| JEL: | G14 |
| Date: | 2025–10–16 |
| URL: | https://d.repec.org/n?u=RePEc:pra:mprapa:126960 |