Stock Return Prediction Based on CNN Model and Genetic Evolutionary Algorithm For A-share Medical Sector

Abstract

Since the outbreak of the epidemic in December 2019, the real economy has been seriously affected, where the stock market has experienced a short-term crash. In this context, the financial market has become more turbulent and unpredictable. Previously, the traditional prediction method only captures the linear relationship between both the dependent and the independent variable. With the growing advancement of technology and science, the application of deep learning models to learn the nonlinear relationship between high latitude indicators and predictors has become the mainstream trend of stock prediction. Therefore, a convolutional neural network (CNN) model with fusion genetic algorithm is proposed in this paper to predict and analyze the stock return rate of China’s A-share medical sector from January 1,2020 to February 2020. In order to facilitate the operation, this paper chooses the GPU with better performance to process the large-scale calculation in the neural network and builds the experimental environment under the Huawei cloud model arts notebook system. This paper selects the Sequential model belonging to the tensor flow library Keras package. Subsequently, this paper optimizes the parameters in the model by using genetic algorithm. According to the analysis, the mean square error of the optimal model is 0.0017, and the prediction results of the model in the test set are validated with well performances, which is of great significance to investors' decision-making. These results shed light on guiding further exploration of stock trend prediction.