{"slug": "defaultgnn-a-dual-perspective-gnn-framework-for-predicting-corporate-default", "title": "DefaultGNN: A Dual-Perspective GNN Framework for Predicting Corporate Default from Buyer-Seller Transaction Networks", "summary": "Researchers proposed DefaultGNN, a dual-perspective graph neural network framework that predicts corporate default from multiplex buyer-view and seller-view transaction networks built on six years of real-world electronic tax-invoice data. In collaboration with a licensed credit rating agency, the researchers validated that DefaultGNN's predictions complement existing credit scoring models, improving approval rates by 7-11 percentage points without increasing default risk among approved firms, according to the arXiv paper. The framework outperformed attribute-based and graph-based baselines, particularly for firms with limited intrinsic risk signals, and source code is available at https://github.com/jhkim611/DefaultGNN.", "body_md": "arXiv:2609.25542v1 Announce Type: new \nAbstract: Corporate default prediction is a core problem in financial risk management, yet traditional credit models rely heavily on financial statements that are often sparse or unavailable for many firms. Corporate transaction networks offer a complementary view of real economic activity, but how risk propagates through buyer-seller relationships remains underexplored. We conduct a large-scale empirical study using real-world electronic tax-invoice data spanning six years that links transaction histories with default events, revealing that transaction-driven risk is both role-dependent (buyer or seller) and scale-dependent. Based on these findings, we construct multiplex buyer-view and seller-view transaction networks and propose DefaultGNN, a dual-perspective graph neural network-based framework for corporate default prediction. DefaultGNN integrates both views to model how risk flows through transactional relationships, achieving strong improvements over both attribute-based and graph-based baselines, especially for firms with limited intrinsic risk signals. We further provide interpretable network-based explanations by visualizing how distressed trading partners contribute to default risk. In collaboration with a licensed credit rating agency, we validate that DefaultGNN's predictions complement existing credit scoring models, improving approval rates by 7-11%p without increasing default risk among approved firms. The source code can be found at https://github.com/jhkim611/DefaultGNN", "url": "https://wpnews.pro/news/defaultgnn-a-dual-perspective-gnn-framework-for-predicting-corporate-default", "canonical_source": "https://www.machinebrief.com/news/defaultgnn-a-dual-perspective-gnn-framework-for-predicting-c-v2yv", "published_at": "2026-09-23 04:00:00+00:00", "updated_at": "2026-09-23 04:54:52.519974+00:00", "lang": "en", "topics": ["machine-learning", "neural-networks", "ai-research"], "entities": ["DefaultGNN", "arXiv", "GitHub"], "alternates": {"html": "https://wpnews.pro/news/defaultgnn-a-dual-perspective-gnn-framework-for-predicting-corporate-default", "markdown": "https://wpnews.pro/news/defaultgnn-a-dual-perspective-gnn-framework-for-predicting-corporate-default.md", "text": "https://wpnews.pro/news/defaultgnn-a-dual-perspective-gnn-framework-for-predicting-corporate-default.txt", "jsonld": "https://wpnews.pro/news/defaultgnn-a-dual-perspective-gnn-framework-for-predicting-corporate-default.jsonld"}}