# Transforming Credit Risk Analysis: A Time-Series-Driven ResE-BiLSTM Framework for Post-Loan Default Detection

arXiv: https://arxiv.org/abs/2508.00415 · HTML: https://mlsanity.com/paper/2508.00415/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 64 references that are in the map.
- First posted on arXiv 1 Aug 2025.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [An LSTM Network for Highway Trajectory Prediction](https://mlsanity.com/paper/1801.07962/) (2018)
- [A Survey on Explainable Anomaly Detection](https://mlsanity.com/paper/2210.06959/) (2022)
- [Are Self-Attentions Effective for Time Series Forecasting?](https://mlsanity.com/paper/2405.16877/) (2024)
- [A Comparative Analysis of Forecasting Financial Time Series Using ARIMA, LSTM, and BiLSTM](https://mlsanity.com/paper/1911.09512/) (2019)
- [Financial series prediction using Attention LSTM](https://mlsanity.com/paper/1902.10877/) (2019)
- [Attention-based Dynamic Multilayer Graph Neural Networks for Loan Default Prediction](https://mlsanity.com/paper/2402.00299/) (2024)
- [Imputing Missing Observations with Time Sliced Synthetic Minority Oversampling Technique](https://mlsanity.com/paper/2201.05634/) (2022)
- [Stock Market Price Prediction: A Hybrid LSTM and Sequential Self-Attention based Approach](https://mlsanity.com/paper/2308.04419/) (2023)

## Abstract (arXiv)

Prediction of post-loan default is an important task in credit risk management, and can be addressed by detection of financial anomalies using machine learning. This study introduces a ResE-BiLSTM model, using a sliding window technique, and is evaluated on 44 independent cohorts from the extensive Freddie Mac US mortgage dataset, to improve prediction performance. The ResE-BiLSTM is compared with five baseline models: Long Short-Term Memory (LSTM), BiLSTM, Gated Recurrent Units (GRU), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN), across multiple metrics, including Accuracy, Precision, Recall, F1, and AUC. An ablation study was conducted to evaluate the contribution of individual components in the ResE-BiLSTM architecture. Additionally, SHAP analysis was employed to interpret the underlying features the model relied upon for its predictions. Experimental results demonstrate that ResE-BiLSTM achieves superior predictive performance compared to baseline models, underscoring its practical value and applicability in real-world scenarios.