A Deep Neural Network Based Model For Stock Market Prediction

The stock market has gradually become an indispensable part of the securities industry and the entire financial industry, and has attracted more and more investors' attention. Therefore, the analysis and prediction of the stock market trend has great theoretical significance and considerable application value. In this paper, an algorithm based on a deep neural network is proposed to build a stock prediction model. The neural network model is a complex network system formed by a large number of simple neurons widely connected to each other. It is a highly complex nonlinear dynamic learning system that can effectively mine attributes of different dimensions for prediction. This model performs better than other comparative models in predicting the trend of stocks. Specifically, the return value of our neural network model is 1059 higher than the Xgboost algorithm and 2257 higher than the random forest algorithm.