Prediction of stock return by LSTM neural network

Abstract

The role of the stock market in the whole financial market is indispensable. How to obtain the actual trading income and maximize the interests in the trading process has been a problem studied by scholars and financial practitioners for a long time. Deep learning network can extract features from a large number of original data, which has potential advantages for stock market prediction. Based on the Shanghai and Shenzhen stock markets from 2019 to 2021, we use LSTM models, optimized on in-sample period and tested on out-of-sample period, using rolling window approach. We select the right hyperparameters at the beginning of our tests, use RBM preprocessing data, then use LSTM model to obtain expected stock return, to effectively predict future stock market analysis and predictive behavior. Finally, we perform a sensitivity analysis of the main parameters and hyperparameters of the model.