Forecasting Stock Prices Using Stock Correlation Graph: A Graph Convolutional Network Approach

Abstract

Accurate forecasting of stock prices plays an important role in stock investment. With the advancement of AI in Fintech applications, various deep learning models have recently been developed for stock price forecasting. However, these models focus on designing sequence models to capture the temporal dependence from a stock's historical prices (and other information such as technical indicators and news), leaving the information from similar stocks underexplored. To fill this gap, we propose a novel deep learning approach for stock price forecasting, which builds and uses a stock correlation graph <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$G$</tex> where nodes are stocks and edges connect highly price-correlated stocks. Our model combines the graph convolutional network (GCN) and gated recurrent unit (GRU). Specifically, the GCN is used to extract features from the price of each stock and the prices of those highly similar stocks in <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">G</tex> . For each stock, a sequence of these extracted features are then fed into a GRU model to capture temporal dependence. The model training follows the idea of multi-task learning, where each task learns its unique RNN-based sequence predictor for one stock, but all stocks share a common GCN module to improve GCN training to more effectively propagate correlation-related market signals. Our extensive experiments on real stock price data demonstrate that our approach consistently outperforms a GRU baseline that does not consider similar stocks during prediction, which verifies the effectiveness of using a stock correlation graph.