GNN-MAM: A graph neural network based multiple attention mechanism for regional financial risk prediction

By combining graph neural networks and multiple attention mechanisms, a GNN-MAM (Graph neural network based on multiple attention mechanisms) model was developed, which utilizes the structural characteristics of graph neural networks to capture complex correlations and dynamic changes in financial d...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuli Ma, MyeongCheol Choi, Yelin Weng
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Alexandria Engineering Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1110016825007641
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849229295005728768
author Yuli Ma
MyeongCheol Choi
Yelin Weng
author_facet Yuli Ma
MyeongCheol Choi
Yelin Weng
author_sort Yuli Ma
collection DOAJ
description By combining graph neural networks and multiple attention mechanisms, a GNN-MAM (Graph neural network based on multiple attention mechanisms) model was developed, which utilizes the structural characteristics of graph neural networks to capture complex correlations and dynamic changes in financial data. Meanwhile, by introducing multiple attention mechanisms, the model can adaptively focus on key information and features in the data, thereby improving the accuracy and robustness of predictions. The experimental results show that compared with traditional financial risk prediction methods, GNN-MAM exhibits higher accuracy and robustness in regional financial risk prediction. Especially when dealing with datasets containing outliers, the predictive performance of GNN-MAM is significantly better than other methods, and the false positive rate is significantly reduced.
format Article
id doaj-art-38ecc281cd3443568917d75f5cb5a6ad
institution Kabale University
issn 1110-0168
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Alexandria Engineering Journal
spelling doaj-art-38ecc281cd3443568917d75f5cb5a6ad2025-08-22T04:55:33ZengElsevierAlexandria Engineering Journal1110-01682025-08-011271004101410.1016/j.aej.2025.06.023GNN-MAM: A graph neural network based multiple attention mechanism for regional financial risk predictionYuli Ma0MyeongCheol Choi1Yelin Weng2School of Economics and Management, Hubei University of Engineering, Xiaogan, Hubei 432000, China; Corresponding author.Department of Business, Gachon University, Seongnam, Gyeonggi-do 13120, Republic of KoreaCollege of Intelligent Engineering and Technology, Jiangsu Vocational and Technical College of Finance and Economics, Huaian, Jiangsu 223003, ChinaBy combining graph neural networks and multiple attention mechanisms, a GNN-MAM (Graph neural network based on multiple attention mechanisms) model was developed, which utilizes the structural characteristics of graph neural networks to capture complex correlations and dynamic changes in financial data. Meanwhile, by introducing multiple attention mechanisms, the model can adaptively focus on key information and features in the data, thereby improving the accuracy and robustness of predictions. The experimental results show that compared with traditional financial risk prediction methods, GNN-MAM exhibits higher accuracy and robustness in regional financial risk prediction. Especially when dealing with datasets containing outliers, the predictive performance of GNN-MAM is significantly better than other methods, and the false positive rate is significantly reduced.http://www.sciencedirect.com/science/article/pii/S1110016825007641GNNMultiple attention mechanismsFinancial risk predictionFinancial Network Analysis
spellingShingle Yuli Ma
MyeongCheol Choi
Yelin Weng
GNN-MAM: A graph neural network based multiple attention mechanism for regional financial risk prediction
Alexandria Engineering Journal
GNN
Multiple attention mechanisms
Financial risk prediction
Financial Network Analysis
title GNN-MAM: A graph neural network based multiple attention mechanism for regional financial risk prediction
title_full GNN-MAM: A graph neural network based multiple attention mechanism for regional financial risk prediction
title_fullStr GNN-MAM: A graph neural network based multiple attention mechanism for regional financial risk prediction
title_full_unstemmed GNN-MAM: A graph neural network based multiple attention mechanism for regional financial risk prediction
title_short GNN-MAM: A graph neural network based multiple attention mechanism for regional financial risk prediction
title_sort gnn mam a graph neural network based multiple attention mechanism for regional financial risk prediction
topic GNN
Multiple attention mechanisms
Financial risk prediction
Financial Network Analysis
url http://www.sciencedirect.com/science/article/pii/S1110016825007641
work_keys_str_mv AT yulima gnnmamagraphneuralnetworkbasedmultipleattentionmechanismforregionalfinancialriskprediction
AT myeongcheolchoi gnnmamagraphneuralnetworkbasedmultipleattentionmechanismforregionalfinancialriskprediction
AT yelinweng gnnmamagraphneuralnetworkbasedmultipleattentionmechanismforregionalfinancialriskprediction