Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.19383 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912446684332032 |
|---|---|
| author | Shreya Pathak, Harsh |
| author_facet | Shreya Pathak, Harsh |
| contents | This paper presents an intelligent and transparent AI-driven system for Credit Risk Assessment using three state-of-the-art ensemble machine learning models combined with Explainable AI (XAI) techniques. The system leverages XGBoost, LightGBM, and Random Forest algorithms for predictive analysis of loan default risks, addressing the challenges of model interpretability using SHAP and LIME. Preprocessing steps include custom imputation, one-hot encoding, and standardization. Class imbalance is managed using SMOTE, and hyperparameter tuning is performed with GridSearchCV. The model is evaluated on multiple performance metrics including ROC-AUC, precision, recall, and F1-score. LightGBM emerges as the most business-optimal model with the highest accuracy and best trade off between approval and default rates. Furthermore, the system generates applicant-specific XAI visual reports and business impact summaries to ensure transparent decision-making. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_19383 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Explainable Artificial Intelligence Credit Risk Assessment using Machine Learning Shreya Pathak, Harsh Machine Learning 68T05 (Primary), 91G40, 62H30, 90B50 (Secondary) I.2.6; I.2.4; H.4.2; J.1 This paper presents an intelligent and transparent AI-driven system for Credit Risk Assessment using three state-of-the-art ensemble machine learning models combined with Explainable AI (XAI) techniques. The system leverages XGBoost, LightGBM, and Random Forest algorithms for predictive analysis of loan default risks, addressing the challenges of model interpretability using SHAP and LIME. Preprocessing steps include custom imputation, one-hot encoding, and standardization. Class imbalance is managed using SMOTE, and hyperparameter tuning is performed with GridSearchCV. The model is evaluated on multiple performance metrics including ROC-AUC, precision, recall, and F1-score. LightGBM emerges as the most business-optimal model with the highest accuracy and best trade off between approval and default rates. Furthermore, the system generates applicant-specific XAI visual reports and business impact summaries to ensure transparent decision-making. |
| title | Explainable Artificial Intelligence Credit Risk Assessment using Machine Learning |
| topic | Machine Learning 68T05 (Primary), 91G40, 62H30, 90B50 (Secondary) I.2.6; I.2.4; H.4.2; J.1 |
| url | https://arxiv.org/abs/2506.19383 |