A novel CBAMs-BiLSTM model for Chinese stock market forecasting

Abstract

The convolutional block attention module (CBAM) has demonstrated its superiority in various prediction problems, as it effectively enhances the prediction accuracy of deep learning models. However, there has been limited research testing the effectiveness of CBAM in predicting stock indexes. To address this gap and improve the prediction accuracy of stock indexes, we propose a novel model called CBAMs-BiLSTM, which combines multiple CBAM modules with a bidirectional long short-term memory network (BiLSTM). In this study, we employ the standard metric evaluation method (SME) and the model confidence set test method (MCS) to comprehensively evaluate the superiority and robustness of our models. We utilize several representative Chinese stock index data sets, namely, the Shanghai (Securities) Composite Index and the Shenzhen Composite Index, as our experimental data. The numerical results demonstrate that CBAMs-BiLSTM outperforms BiLSTM alone, achieving average reductions of 13.06%, 13.39%, and 12.48% in MAE, RMSE, and MAPE, respectively. These findings confirm that CBAM can effectively enhance the prediction accuracy of BiLSTM. Furthermore, we compare our proposed model with other popular models and examine the impact of changing data sets, prediction methods, and the size of the training set. The results consistently demonstrate the superiority and robustness of our proposed model in terms of prediction accuracy and investment returns.