From Wall Street to Heartbeat: AI Forecasting for Financial Volatility and Investor Well-Being

Abstract

This study proposes an explainable deep learning framework for stock price forecasting that addresses both predictive performance and the health implications of financial volatility, particularly its link to cardiovascular risk. The model integrates Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and one-dimensional Convolutional Neural Network (CNN) architectures, trained on multivariate OHLCV (Open, High, Low, Close, Volume) of stock market data from the S&P 500 over the period 2019 to 2023, with a lookback horizon of thirty days. To improve interpretability and behavioral usability, the framework incorporates SHapley Additive Explanations (SHAP) and Local Interpretable ModelAgnostic Explanations (LIME). These tools enhance transparency, reduce ambiguity aversion, and promote trust, which is critical for users facing emotionally charged financial decisions that may exacerbate cardiovascular stress. Empirical results show that the LSTM achieves the strongest predictive performance, with statistically significant outperformance over GRU and CNN verified via Diebold-Mariano tests. SHAP identifies ‘Close’ price and ‘Volume’ as dominant features, while LIME confirms consistent local interpretability across recurrent models. By combining accurate forecasting with interpretable AI, the proposed framework not only enhances decision making in algorithmic trading and portfolio management, but also contributes to reducing stress-induced health risks associated with market uncertainty.