HDML: hybrid data-driven multi-task learning for China’s stock price forecast

Abstract

Recent years have witnessed the rapid development of the China’s stock market, but investment risks have also emerged. Stock price is always unstable and non-linear, affected not only by historical transaction data but also by national policies, news, and other data. Stock price and textual data are beginning to be employed in the prediction process. However, the challenge lies in effectively integrating feature information derived from stock price and textual information. To address the problem, in this paper, this paper proposes a Hybrid Data-driven Multi-task Learning(HDML) framework to predict stock price. HDML adopts hybrid data as model input, mining the transaction and capital flow data information in the stock market and considering the impact of investors’ emotions on the stock market. In addition, we incorporate multi-task learning, which predicts the closing price range of stock based on structured data and then corrects the prediction results through investors’ comment text data. HDML effectively captures the relationship between different modal data through multi-task learning and achieve improvements on both tasks. The experimental results show that compared with previous work, HDML reduces the RMSE of the evaluation set by 12.14% and improves the F1 score by an average of 13.64% at the same time. Moreover, value at risk (VaR), together with the HDML model, can help investors weigh the potential gains against the associated risks.