Firm Default Prediction by GNN with Gravity-Model Informed Neighbor Node Sampling

Naoto Minakawa (), Kiyoshi Izumi (), Yuri Murayama () and Hiroki Sakaji ()
Additional contact information
Naoto Minakawa: The University of Tokyo
Kiyoshi Izumi: The University of Tokyo
Yuri Murayama: The University of Tokyo
Hiroki Sakaji: Hokkaido University

The Review of Socionetwork Strategies, 2024, vol. 18, issue 2, 303-328

Abstract: Abstract Firm default prediction is important in credit risk management and understanding economic trends. Both practitioners and academic researchers have long studied it. While traditional statistical methods such as discriminant analysis and logistic regression have been used recently, machine learning and deep learning methods have been widely applied. The graph neural network (GNN) is one of the latest applications of deep-learning approaches. With the use of GNNs, it is possible to reflect the non-linear relationships of features among neighboring companies around the target company, whereas ordinary machine learning and deep learning methods focus only on the features of the target company. However, when handling large-scale graphs such as inter-firm networks, it is difficult to apply vanilla GNNs naively. Although uniform neighbor node sampling is commonly used for large-scale graphs, to the best of our knowledge, no research has focused on better sampling methods for GNN applications for default prediction. From the practical viewpoint, it means which companies should be considered with priority for firm default prediction. In this study, we propose a novel gravity model-informed neighbor sampling method based on the estimated transaction volume by utilizing knowledge from econophysics. The scope of this research is to determine whether we can improve default predictions by considering neighboring companies with larger transaction amounts compared to ordinary uniform sampling. We also verified that the proposed method improves the prediction performance and stability compared to GNNs with other sampling techniques and other machine learning methods using real large-scale inter-firm network data.

Keywords: Default prediction; Credit risk management; Graph neural networks; Gravity model; Inter-firm network (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s12626-024-00170-6 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:trosos:v:18:y:2024:i:2:d:10.1007_s12626-024-00170-6

Ordering information: This journal article can be ordered from
https://www.springer ... ystems/journal/12626

DOI: 10.1007/s12626-024-00170-6

Access Statistics for this article

The Review of Socionetwork Strategies is currently edited by Katsutoshi Yada, Yasuharu Ukai and Marshall Van Alstyne

More articles in The Review of Socionetwork Strategies from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().