CausalSeqGNN: A Fama-French Inspired Fuzzy Cognitive Map Combined With Graph Neural Network for Stock Prediction

Accurate stock prediction is a pressing challenge in quantitative finance, where complex temporal and cross-sectional dynamics defy traditional models. Although deep learning-based methods have made significant progress, most of them focus on individual stock trajectories, neglecting directional causality in stock interactions. Fuzzy cognitive maps (FCMs) are good at modeling the directional causality. Therefore, we design a new type of FCM with each concept node having a fuzzy state vector instead of just a fuzzy state value to more stereoscopic manifest the factors affecting a stock, like firm size, book-to-market value, and market risk emphasized by the famous Fama-French multifactor model. A genetic algorithm with a specially designed objective function is used to learn the new FCMs. Furthermore, the new FCMs are combined with a double-level attention mechanism and graph neural networks (GNNs) for z-score forecasting, named CausalSeqGNN. To balance scalability and adaptability, a dual-phase alternating learning architecture is designed in CausalSeqGNN, where the double-level attention mechanism fuses eight-day price sequences with news-derived sentiment scores updated daily, and the causal matrix capturing asymmetric stock interdependencies obtained by FCM learning updated quarterly since companies generally release their financial reports on a quarterly basis. Successfully synergizing Fama-French-driven causality with temporal dynamics, CausalSeqGNN achieves superior mean squared error and investment performance on US and Chinese market dataset, outperforming state-of-the-art baselines. This hybrid framework offers transformative potential for real-time trading, redefining stock forecasting with unparalleled precision and scalability.