Stock Price Prediction Using LSTM Neural Network

As a method of asset allocation,stocks have always been favored by investors because of their high returns.Investors have never stopped studying stock price predictions.In the early days,many economists tried to predict stock prices.Later,with the in-depth research of mathematical theory and the vigorous development of computer technology,it was found that mathematical models can solve the problem well,such as time series models.Because of their simple model intersections and good forecasting effects,they can be used in a certain period of time.Gradually expand.However,due to the non-linearity of stock data,some machine learning methods have gradually entered the field of researchers,such as support vector machines.Later,with the development of deep learning,some such as RNN and LSTM neural networks have gradually become new to researchers.Beloved,they can not only process non-linear data,but also retain memory for the sequence and retain useful information,which is exactly what the stock data forecast needs.This article provides theoretical knowledge of LSTM neural and time series models,selects actual stocks in the stock market,performs modeling analysis and predicts stock prices,and then uses RMSE to compare the prediction results of several models.Since the time series model cannot make full use of the non-linear part of the data and cannot carry out long-term memory,the LSTM neural network can make full use of the non-linear data and long-term memory to obtain useful information in the stock data.As far as the root mean square error is concerned,the LSTM neural network is smaller than the time series model,which shows that the LSTM neural network is a better method for predicting stock prices.