Unveiling the Predictive Power: Comparative Analysis of Cutting-Edge Deep Learning Models for Stock Price Forecasting

Abstract

Accurate stock price prediction plays a fundamental role in informing government financial regulations and facilitating effective arbitrage strategies for investors. With the application of deep learning algorithms in finance, significant progress has been made to improve the accuracy of stock price prediction. In this paper, first, we collected stock price data from four listed companies from different sectors. Then, we used four competitive methods for prediction, namely LSTM, GRU-LSTM, Attention-LSTM and Transformer-LSTM. The validity of the study is supported by multiple sets of comparative experiments. Our experimental results show that LSTM shows superiority in predicting stock prices, while Transformer-LSTM model has better generalization ability.