A self-regulated generative adversarial network for stock price movement prediction based on the historical price and tweets

摘要

Stock price movement prediction is an important task of the financial prediction field. The current mainstream approaches usually apply financial texts and some corresponding stock price information to predict the stock price movement. However, the current methods usually suffer from two shortcomings: (1) To reduce the stochasticity in the stock price and financial text information, some researchers adopt generative models to better treat the stochasticity while enduring the overfitting problem during training. (2) Although the current state-of-the-art methods based on the generative adversarial network have been proposed to reduce the overfitting, they only concentrate on the overfitting problem of the stock price information and neglect the above problem of financial text information with higher stochasticity. In this paper, we propose a self-regulated generative adversarial network by combining the generative adversarial network and cooperative network for the stock price movement prediction. Furthermore, the proposed model can effectively reduce the stochasticity and overfitting problems simultaneously for the stock price and the financial text information. The experimental results on the currently commonly used stock dataset based on tweets confirm that the proposed method can achieve the novelly state-of-the-art performance compared with some current advances.