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

TL;DR

This paper presents a novel ResE-BiLSTM framework utilizing time-series data and a sliding window approach to enhance post-loan default prediction accuracy in credit risk management, validated on extensive mortgage datasets.

Contribution

Introduces a ResE-BiLSTM model with a sliding window technique for improved default prediction, outperforming traditional models in credit risk analysis.

Findings

ResE-BiLSTM outperforms baseline models in accuracy, precision, recall, F1, and AUC.

Ablation study highlights the importance of each component in the architecture.

SHAP analysis provides interpretability of the model's predictions.

Abstract

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.