Explainable AI-Driven Credit Risk Assessment and Financial Decision Support Using Random Forest, LIME, and SHAP
ID：72
Submission ID：432 View Protection：ATTENDEE
Updated Time：2026-07-22 16:09:39 Hits：34
Online
Start Time：2026-07-31 11:55 （Asia/Kolkata）
Duration：15min
Session：[S1] 5G and beyond Wireless Networks » [S1-4] 5G and beyond Wireless Networks
Presentation File
Tips: The file permissions under this presentation are only for participants. You have not logged in yet and cannot view it temporarily.
Abstract
Credit-risk assessment is a high-impact financial task, as automated loan decisions influence portfolio quality, institutional profitability, regulatory compliance, and customer access to credit. Machine learning models can increase the predictive power, but black-box predictions are hard to justify in regulated financial settings. In this paper, we propose a novel explainable artificial intelligence (XAI) decision-support framework for credit-risk assessment, based on decision tree and random forest classifiers combined with Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP). This approach extends the original experimental design with explicit steps of preprocessing, imbalance treatment, model training, evaluation and explanation. Results are discussed in terms of accuracy, precision, recall, and F1-score, as well as, behaviors of the confusion matrix, feature importance analysis, explanations at the local applicant level, and a governance-oriented financial interpretation. The enhanced framework demonstrates how XAI can transform a predictive credit model into a transparent, auditable and policy-relevant decision support system for banks, credit officers, risk committees and borrowers.
Keywords
Credit risk assessment, explainable artificial intelligence, financial decision support, random forest, decision tree, LIME, SHAP, model governance.
Speaker
Comment submit