Abstract
Stock price prediction is an important and challenging problem for studying financial markets. Existing studies are mainly based on the time series of stock price or the operation performance of listed company. In this paper, we propose to predict stock price based on investors' trading behavior. For each stock, we characterize the daily trading relationship among its investors using a trading network. We then classify the nodes of trading network into three roles according to their connectivity pattern. Strong Granger causality is found between stock price and trading relationship indices, i.e., the fraction of trading relationship among nodes with different roles. We further predict stock price by incorporating these trading relationship indices into a neural network based on time series of stock price. Experimental results on 51 stocks in two Chinese Stock Exchanges demonstrate the accuracy of stock price prediction is significantly improved by the inclusion of trading relationship indices.
Highlights
Using Granger causality analysis, we find that stock price is strongly correlated with trading relationship indices, i.e., the fraction of trading relationship among different kinds of nodes. By combining these trading relationship indices together with time series of stock price, we propose a stock price prediction model based on feed forward neural network
We investigated the problem of stock price prediction for individual stock rather than predicting global indices of stock market as done by traditional studies
Taking stock trading network as a proxy, we study whether trading behavior could predict the change of stock price
Summary
We further predict stock price by incorporating these trading relationship indices into a neural network based on time series of stock price. Efficient-market hypothesis states that stock price is a full reflection of all relevant information This implies that current stock price is basically determined by currently available information rather than past prices. Bollen et al argued that some predictive indicators could be extracted from online website stock price is affected by certain unpredicted news or exogenous shock. They proposed to use the collective mood states derived from Twitter to predict the value of the Dow Jones Industrial Average with the accuracy up to 87.6 percent[9].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
