Application And Analysis Of Stock Price Forecasting Model Based On BP Neural Network

As an indispensable part of the financial industry,the stock investment is becoming more and more important in people's life.The fluctuation of stock price has a direct impact on the stability of the stock market and the healthy development of the financial market and the national economy.The success of the stock price and trend forecast will help investors to profit,but also help the government departments to provide timely and reasonable market guidance and supervision.Therefore,how to predict the stock market is an important and valuable topic in the financial field.Neural network can simulate the function of human neurons,which can extract the historical data and related information from the stock market to infer the future development trend of stock price.Therefore,neural network is suitable for dealing with the problem of stock price forecasting with nonlinear time series.In this paper,an integrated model of stock price forecasting based on BP neural network is proposed.The discussion from the impact of price factors in the market and identified 21 evaluation index for stock price forecasting,reduced to 6 input variables by principal component analysis method;at the same time through the optimization of the network initial weights and thresholds of mind evolutionary algorithm;discusses the topology structure and the number of hidden layer nodes and learning rate,and the activation function the training function,the sample data selection and processing of network;finally established the comparison model and through multiple runs,comprehensive model has the highest prediction accuracy and stability.Theoretical analysis and experimental results show that the BP based neural network model is feasible and effective,and has a good application prospect.