Higher-order Graph Attention Network for Stock Selection with Joint Analysis
This work addresses stock prediction for investors by improving graph neural network methods, though it appears incremental as it builds on existing GNN approaches with specific enhancements.
The paper tackles stock selection by proposing a higher-order graph attention network (H-GAT) that captures complex higher-order structures and jointly incorporates fundamental and technical analysis factors, achieving superior profitability and Sharpe ratio on NASDAQ and NYSE datasets.
Stock selection is important for investors to construct profitable portfolios. Graph neural networks (GNNs) are increasingly attracting researchers for stock prediction due to their strong ability of relation modelling and generalisation. However, the existing GNN methods only focus on simple pairwise stock relation and do not capture complex higher-order structures modelling relations more than two nodes. In addition, they only consider factors of technical analysis and overlook factors of fundamental analysis that can affect the stock trend significantly. Motivated by them, we propose higher-order graph attention network with joint analysis (H-GAT). H-GAT is able to capture higher-order structures and jointly incorporate factors of fundamental analysis with factors of technical analysis. Specifically, the sequential layer of H-GAT take both types of factors as the input of a long-short term memory model. The relation embedding layer of H-GAT constructs a higher-order graph and learn node embedding with GAT. We then predict the ranks of stock return. Extensive experiments demonstrate the superiority of our H-GAT method on the profitability test and Sharp ratio over both NSDAQ and NYSE datasets