Stock Trend Prediction based on Wide & Deep Asymmetrical Bidirectional Legendre Memory Units

Deep learning technology has been widely applied in the finance industry, particularly in the study of stock price prediction. This paper focuses on the prediction accuracy and performance of long-term features and proposes a Wide & Deep Asymmetrical Bidirectional Legendre Memory Units that captures long-term dependencies in time series through the immediate backpropagation of bidirectional recurrent modules and Legendre polynomial memory units. The proposed model achieves superior stock trend prediction capabilities by combining the memory and generalization capabilities of the Wide & Deep model. Experimental results on the daily trading data set of the constituents of the CSI 300 index demonstrate that the proposed model outperforms several baseline models in medium and long-term trend prediction.