An Explainable Machine Learning Framework for Dynamic Credit Portfolio Risk Assessment and Default Prediction Using Random Forest Optimization

JAYANTHI KANNAN; Samikshya Pruseth

doi:10.36948/ijfmr.2026.v08i02.73602

An Explainable Machine Learning Framework for Dynamic Credit Portfolio Risk Assessment and Default Prediction Using Random Forest Optimization

Author(s)	Dr. JAYANTHI KANNAN, Ms. Samikshya Pruseth
Country	India
Abstract	Credit risk assessment is a cornerstone of financial stability, yet traditional evaluation methods—largely manual, heuristic, or based on simplistic logistic regression—suffer from low predictive power and an inability to capture non-linear relationships in borrower data. This research presents a web-based decision support system, the Credit Portfolio Risk and Default Prediction System (CPRD-PS) , which integrates advanced data preprocessing, a hyperparameter-optimized Random Forest classifier, and interactive visualization dashboards. The system predicts probability of default (PD) at both individual loan and portfolio levels. Evaluated on a synthetic but statistically realistic consumer credit dataset, the proposed model achieves an AUC-ROC of 0.94, an F1-score of 0.89, and reduces Type II errors (costly default misclassifications) by 23% compared to baseline logistic regression. The system further incorporates SHAP (SHapley Additive exPlanations) for model interpretability, addressing regulatory demands for explainable AI (XAI) in finance. This research demonstrates that a well-tuned ensemble method, combined with real-time risk dashboards, can significantly enhance data-driven lending decisions.
Keywords	Credit Risk, Machine Learning, Loan Default Prediction, Random Forest, Financial Analytics, Decision Support System, Explainable AI.
Field	Computer Applications
Published In	Volume 8, Issue 2, March-April 2026
Published On	2026-04-09
DOI	https://doi.org/10.36948/ijfmr.2026.v08i02.73602

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 2 Cover Page Vol 8 Isu 1 Cover Page Vol 7 Isu 6

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

An Explainable Machine Learning Framework for Dynamic Credit Portfolio Risk Assessment and Default Prediction Using Random Forest Optimization

Share this