# Relational Graph Modeling for Credit Default Prediction: Heterogeneous GNNs and Hybrid Ensemble Learning

arXiv: https://arxiv.org/abs/2601.14633 · HTML: https://mlsanity.com/paper/2601.14633/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 13 references that are in the map.
- First posted on arXiv 21 Jan 2026.

## Builds on (most cited first, 2 of 2)

- [A Review on Graph Neural Network Methods in Financial Applications](https://mlsanity.com/paper/2111.15367/) (2021)
- [Ensemble Methodology:Innovations in Credit Default Prediction Using LightGBM, XGBoost, and LocalEnsemble](https://mlsanity.com/paper/2402.17979/) (2024)

## Built on by (most cited first, 1 of 1)

- [Subgraph Filtering for Fair Graph Neural Networks](https://mlsanity.com/paper/2608.26437/) (2026)

## Abstract (arXiv)

Credit default risk arises from complex interactions among borrowers, financial institutions, and transaction-level behaviors. While strong tabular models remain highly competitive in credit scoring, they may fail to explicitly capture cross-entity dependencies embedded in multi-table financial histories. In this work, we construct a massive-scale heterogeneous graph containing over 31 million nodes and more than 50 million edges, integrating borrower attributes with granular transaction-level entities such as installment payments, POS cash balances, and credit card histories. We evaluate heterogeneous graph neural networks (GNNs), including heterogeneous GraphSAGE and a relation-aware attentive heterogeneous GNN, against strong tabular baselines. We find that standalone GNNs provide limited lift over a competitive gradient-boosted tree baseline, while a hybrid ensemble that augments tabular features with GNN-derived customer embeddings achieves the best overall performance, improving both ROC-AUC and PR-AUC. We further observe that contrastive pretraining can improve optimization stability but yields limited downstream gains under generic graph augmentations. Finally, we conduct structured explainability and fairness analyses to characterize how relational signals affect subgroup behavior and screening-oriented outcomes.