Interpretable ESG–sentiment hybrid deep learning for asset return forecasting with quantified interactions and latency-aware deployment

Unofficial AI-generated summary based on the public title and abstract. Not an official translation.

🔬研究者:Provides a rigorous framework for quantifying ESG–sentiment interactions with regime dependence and latency-aware deployment, with robust statistical tests.

🏢実務担当者:Offers a latency-optimized model that can be integrated into near-real-time trading systems, with clear evidence of improved risk-adjusted returns when incorporating ESG signals.

Accurate forecasting of financial time series increasingly relies on alternative data such as environmental, social and governance (ESG) scores and news-based sentiment, yet the way these signals interact and when they actually improve forecasts is still poorly understood. We introduce an interpretable hybrid framework for asset return forecasting that combines a Temporal Fusion Transformer (TFT) with a lightweight Support Vector Regression (SVR) residual corrector and an explicit gated late fusion of ESG features with aspect-based financial sentiment (FinBERT-based ABSA). The gating mechanism learns when to emphasize sustainability versus sentiment signals, while SHAP interaction values and Friedman’s H quantify ESG–sentiment interactions across assets and regimes. A finance-grade, leak-proof walk-forward protocol (252 trading days train / 10 days test, within-fold scaling, ABSA items strictly before 16:00 ET; ESG effective T+3; macro T+1, HAC-robust Diebold–Mariano tests) is applied to US large-cap technology equities, major global indices, and BTC/ETH over 2020–2024. Across \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$n=5$$\end{document} independent seeds, the hybrid achieves aggregate mean absolute error of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$2.77\times 10^{-3}$$\end{document} and RMSE of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$5.18\times 10^{-3}$$\end{document} on next-day log returns, with directional accuracy \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$94.5\%$$\end{document}, IC 0.39, and ICIR 0.82, significantly outperforming tuned deep-learning and machine-learning baselines (HAC-robust per-asset Diebold–Mariano tests with BH-FDR \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$q=0.05$$\end{document}; Fisher aggregation yields \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$p<0.01$$\end{document}). Simple long-only, thresholded simulations indicate higher risk-adjusted performance and lower maximum drawdown under conservative transaction-cost assumptions. Ablation studies show that removing either ESG or sentiment features yields the largest degradations, and that the SVR corrector stabilizes errors under regime shifts. To directly address market-cycle sensitivity, we evaluate stability across event-defined stress windows (COVID-19 crash, 2022 tightening cycle, and 2023 banking stress) and volatility-defined regimes using terciles of 20-day realized volatility. We report regime-split forecasting and strategy metrics with block-bootstrap confidence intervals, HAC-robust Diebold–Mariano tests within each regime, and residual-stabilization diagnostics that quantify the SVR variance and skewness reduction under stress. ESG–sentiment interactions are statistically non-zero and regime-dependent, with sentiment gaining importance in turbulent periods and ESG in calmer markets. A latency-optimized variant that removes auxiliary BiLSTMs retains over \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$90\%$$\end{document} of the accuracy gains while reducing inference time by approximately \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$55\%$$\end{document} of the full model (i.e., a reduction of about \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$45\%$$\end{document}), supporting near-real-time deployment.

• semanticscholar https://doi.org/10.1038/s41598-026-41985-3first seen 2026-07-18 08:13:28