Multivariate Realized Volatility Forecasting with Graph Neural Network
This addresses stock market volatility prediction for financial analysts, but appears incremental as it applies a graph neural network variant to an existing problem.
The paper tackles multivariate short-term realized volatility forecasting using limit order book data and relational information between stocks, achieving better performance than benchmarks on approximately 500 S&P 500 stocks.
The existing publications demonstrate that the limit order book data is useful in predicting short-term volatility in stock markets. Since stocks are not independent, changes on one stock can also impact other related stocks. In this paper, we are interested in forecasting short-term realized volatility in a multivariate approach based on limit order book data and relational data. To achieve this goal, we introduce Graph Transformer Network for Volatility Forecasting. The model allows to combine limit order book features and an unlimited number of temporal and cross-sectional relations from different sources. Through experiments based on about 500 stocks from S&P 500 index, we find a better performance for our model than for other benchmarks.