Stock price prediction based on PCA-LSTM model

Abstract

In order to improve the prediction accuracy, this study proposes an new PCA-LSTM neural network stock price prediction model that combines principal component analysis(PCA) and long-term and short-term memory neural network (LSTM). We download time series indicators and technical indicators of PingAn insurance (X601318) form Tushare interface and Wind database. PCA method was used to reduce the technical indicators dimension, LSTM model was used to predict the next day stock closing price. The results show that PCA-LSTM model can greatly reduce data redundancy and obtain better prediction accuracy compared with the simple LSTM model. Additional Keywords and Phrases: stock price prediction, PCA, LSTM