FinHGNN: A conditional heterogeneous graph learning to address relational attributes for stock predictions

Recent financial studies have shown that spillover effects of some market factors play a sig-nificant role in stock fluctuations. Previous studies, however, were incapable of capturing the spillovers of these relational market factors because they relied on a homogeneous graph that condenses these factors into firm node attributes and requires their spillover effects to follow firm relationship instead of themselves. This fact brings up a heteroge-neous graph learning problem that requires multiple node types to transport different spil-lover effects. This study proposes a novel conditional heterogeneous graph neural network (FinHGNN) to capture multiple spillover effects in asset pricing with two uniquely designed mechanisms. First, it presents an efficient way to preserve the connectivity of relational attributes in graph learning, which is achieved by converting relational attributes into node variables to form a heterogeneous graph. Second, a conditional message-passing mechanism is proposed to handle multiple spillover effects simultaneously by messaging conditioned on different types of nodes and node attributes. This study paves the way for addressing the relational attributes in graph learning. Experiments on two real-world datasets demonstrate the advantages of the proposed framework over three classic and four state-of-the-art algorithms, including LSTM, GCN, HGNN, eLSTM, TGC, FinGAT, and AD-GAT. (c) 2022 Elsevier Inc. All rights reserved.

Automated summary

Recent financial studies have shown the significant role of spillover effects of certain market factors in stock fluctuations. This study proposes a novel conditional heterogeneous graph neural network (FinHGNN) to capture multiple spillover effects in asset pricing. Experimental results demonstrate the advantages of the proposed framework over other algorithms on two real-world datasets.