Multi-branch neural networks and its application to stock price prediction

Recently, artificial neural networks have been utilized for financial market applications. We have so far shown that multi-branch neural networks (MBNNs) could have higher representation and generalization ability than conventional NNs. In this paper, a prediction system of a stock price using MBNNs is proposed. Using the stock prices in time series and other information, MBNNs can learn to predict the price of the next day. The result of our simulations shows that the proposed system has better accuracy than a system using conventional NNs.