The Application of Sequential Generative Adversarial Networks for Stock Price Prediction

A significant application of machine learning in the financial field is stock price prediction. Investors can obtain a useful investment reference from the result of a stock prediction model. Stock future trend prediction is mainly divided into fundamental and technical analyses. Before the boom of machine learning, a linear time series forecast algorithm was used widely for stock price prediction. In recent years, with the development of machine learning, state-of-the art algorithms of machine learning such as Long Short-Term Memory (LSTM) and Generative Adversarial Networks (GANs) have been used to forecast stock prices. In previous research, however, only one model has been used for this task. In this work, we use a model which is a combination of Neural Networks such as the Recurrent Neural Network (RNN), the Long Short-Term Memory (LSTM) and the Gated Recurrent Unit (GRU) in a Generative Adversarial Networks (GANs) framework. The proposed algorithms are applied for stock price prediction of data of the S&P 500. In this paper, experiments prove that the proposed model has a better performance in stock price prediction than previous single algorithm prediction research.