GCNET: graph-based prediction of stock price movement using graph convolutional network

The prediction of stocks' direction of movement using the historical price information has attracted considerable attention as a challenging problem in the field of machine learning. However, modeling and analyzing the hidden relations among stock prices as an important source of information for the prediction of their future behavior has not been explored well yet. The existing methods in this domain suffer from the lack of generality and flexibility and cannot be easily applied on any set of inter-related stocks. The main challenges in this domain are to find a way for modeling the existing relations among an arbitrary set of stocks and to exploit such a model for improving the prediction performance for those stocks. In this paper, we introduce a novel framework, called GCNET that models the relations among an arbitrary set of stocks as a graph structure called influence network and uses a set of history-based prediction models to infer plausible initial labels for a subset of the stock nodes in the graph. Finally, GCNET uses the Graph Convolutional Network algorithm to analyzes this partially labeled graph and predicts the next price direction of movement for each stock in the graph. GCNET is a general prediction framework that can be applied for the prediction of the price fluctuations for any set of interacting stocks based on their historical data. Our experiments and evaluations on sets of stocks from S\&P500 and NASDAQ show that GCNET significantly improves the performance of SOTA in terms of accuracy and MCC measures.