Relation-aware dynamic attributed graph attention network for stocks recommendation. (January 2022)

• Record Type: Journal Article
• Authors: Feng, Shibo; Xu, Chen; Zuo, Yu; Chen, Guo; Lin, Fan; XiaHou, Jianbing
• Is Part Of: Pattern recognition. Volume 121(2022)
• Publication Date: 2022-01
• Subjects: Financial market -- Attributed graph attention network -- Correlation coefficient -- Chinese stock recommendation; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2021.108119
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Replacing the task of predicting stock prices and trends in the traditional financial field with a new way of recommending the return ratio of stocks. Introducing the graph convolutional network as a guide to the graph attention network for information aggregation, whose attention mechanism is expanded from node features to topology information to make the stock correlation integrated into the message passing of the stock features. Applying the factor strategy mechanism into the complex stock network to select the important factor components. Abstract: The inherent properties of the graph structure of the financial market and the correlation attributes that actually exist in the system inspire us to introduce the concept of the graph to solve the problem of prediction and recommendation in the financial sector. In this paper, we are adhering to the idea of recommending high return ratio stocks and put forward an attributed graph attention network model based on the correlation information, with encoded timing characteristics derived from time series module and global information originating from the stacked graph neural network(GNN) based models, which we called Relation-aware Dynamic Attributed Graph Attention Network (RA-AGAT). On this basis, we have verified the practicality and applicability of the application of graph models in finance. Our innovative structure first captures the local correlation topology information and then introduce a stacked graph neural network structure to recommend Top-N return ratio of stock items. Experiments on the real China A-share market demonstrate that the RA-AGAT architecture is capable of surpassing the previously applicable methods in the prediction and recommendation of stock return ratio.