Interpretable ESG-sentiment hybrid deep learning for asset return forecasting with quantified interactions and...

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 [Formula: see text] independent seeds, the hybrid achieves aggregate mean absolute error of [Formula: see text] and RMSE of [Formula: see text] on next-day log returns, with directional accuracy [Formula: see text], 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 [Formula: see text]; Fisher aggregation yields [Formula: see text]). 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 [Formula: see text] of the accuracy gains while reducing inference time by approximately [Formula: see text] of the full model (i.e., a reduction of about [Formula: see text]), supporting near-real-time deployment.