A Data-Driven Model for Predicting Loan Approval Using Machine Learning Approaches
Sonali Chaurasia, Ankur Kumar Varshney Department of Information Technology, Noida Institute Of Engineering And Technology, Greater Noida, U.P
Abstract
Loan default prediction is essential for financial institutions. This study examines Decision Tree and Random Forest models for credit risk assessment using lending datasets. Results indicate Random Forest’s higher accuracy, making it a preferred choice for predictive analytics in lending.
The research compared Decision Trees and Random Forests for loan default prediction, showing Random Forestβs superior 80% accuracy vs. Decision Treeβs 73%. This suggests Random Forest is a more reliable model for lending institutions seeking risk mitigation.
References
[1] Singh A., Patel R., Kumar S. Challenges of logistic and probit models in credit risk prediction. Journal of Financial Analytics, 12(3), 2023. [2] Zhao X., Li Q., Wang X. Evaluating Random Forests for Credit Risk Prediction. Journal of Financial Data Science, 4(3), 2022. [3] Chen Y., Zhang L., Huang Y. Support Vector Machines for Credit Risk Prediction. International Journal of Data Science and Analytics, 11(1), 2022.
Post Comment