{"ID":2857832,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.07663","arxiv_id":"2510.07663","title":"Incremental Hybrid Ensemble with Graph Attention and Frequency-Domain Features for Stable Long-Term Credit Risk Modeling","abstract":"Predicting long-term loan defaults is hard because borrower behavior often changes and data distributions shift over time. This paper presents HYDRA-EI, a hybrid ensemble incremental learning framework. It uses several stages of feature processing and combines multiple models. The framework builds relational, cross, and frequency-based features. It uses graph attention, automatic cross-feature creation, and transformations from the frequency domain. HYDRA-EI updates weekly using new data and adjusts the model weights with a simple performance-based method. It works without frequent manual changes or fixed retraining. HYDRA-EI improves model stability and generalization, which makes it useful for long-term credit risk tasks.","short_abstract":"Predicting long-term loan defaults is hard because borrower behavior often changes and data distributions shift over time. This paper presents HYDRA-EI, a hybrid ensemble incremental learning framework. It uses several stages of feature processing and combines multiple models. The framework builds relational, cross, an...","url_abs":"https://arxiv.org/abs/2510.07663","url_pdf":"https://arxiv.org/pdf/2510.07663v1","authors":"[\"Jiajing Wang\"]","published":"2025-10-09T01:31:04Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}