Stock Price Prediction Model Analysis Based on Neural Network

Abstract

As a matter of fact, stock price prediction is always crucial for investors and scholars to gain extra return from the stock market. Thanks to the rapid development of the machine learning techniques as well as computation ability (e.g., GPU), various deep leaning models based on the concepts of neural networks are proposed and applied in stock price prediction. On this basis, this paper will investigate the feasibility of stock price prediction based on various neural network deep learning scenarios. With this in mind, the BP neural network, principal component-based BP neural network (PCA-BP neural network) as well as GA-BP neural network are implemented to realize stock price prediction. In order to compare the effectiveness, the ARIMA model is also adopted as a benchmark. According to the analysis, neural network is suitable for stock price prediction. Overall, these results shed light on guiding further exploration of stock price prediction based on the state-o-art machine learning approaches.