Graph-Based Learning for Stock Movement Prediction with Textual and Relational Data

TL;DR

This paper introduces a Multi-Graph Recurrent Network that integrates textual sentiment and relational data to improve stock movement prediction, outperforming benchmarks in accuracy and trading simulations.

Contribution

The paper presents a novel multi-graph recurrent network architecture that combines textual and relational financial data for enhanced stock prediction.

Findings

Better prediction accuracy than benchmarks

Improved trading simulation performance

Effective integration of textual and relational data

Abstract

Predicting stock prices from textual information is a challenging task due to the uncertainty of the market and the difficulty understanding the natural language from a machine's perspective. Previous researches focus mostly on sentiment extraction based on single news. However, the stocks on the financial market can be highly correlated, one news regarding one stock can quickly impact the prices of other stocks. To take this effect into account, we propose a new stock movement prediction framework: Multi-Graph Recurrent Network for Stock Forecasting (MGRN). This architecture allows to combine the textual sentiment from financial news and multiple relational information extracted from other financial data. Through an accuracy test and a trading simulation on the stocks in the STOXX Europe 600 index, we demonstrate a better performance from our model than other benchmarks.