What Borrower Characteristics Best Predict Loan Approval Probability in Peer-To-Peer Lending Platforms, and How Do These Vary Between Models? How Can Small To Medium-Sized Businesses Ameliorate These Factors?

Arush Singhania

doi:10.36948/ijfmr.2025.v07i05.58638

What Borrower Characteristics Best Predict Loan Approval Probability in Peer-To-Peer Lending Platforms, and How Do These Vary Between Models? How Can Small To Medium-Sized Businesses Ameliorate These Factors?

Author(s)	Arush Singhania
Country	India
Abstract	This study examines the application of machine learning models to predict loan outcomes on peer-to-peer lending platforms. It highlights the comparative performance of Logistic Regression, Random Forest and XGBoost, three models that represent distinct balances between interpretability, complexity and predictive power. The research emphasizes predictive accuracy and the importance of model transparency. It illustrates that while ensemble methods, such as Random Forest and XGBoost improve performance, Logistic Regression continues to provide valuable interpretive insights. Findings reveal that credit history features, such as FICO scores, delinquency history and utilization rates are more reliable predictors of repayment than commonly assumed factors such as income or employment length. These results contribute to the literature on credit risk modeling by integrating comparative model evaluation with feature importance analysis to identify the most influential borrower characteristics. Building on these insights, a predictive model was developed to forecast loan outcomes with improved accuracy and interpretability. They carry practical implications for borrowers, lenders and small businesses seeking to understand and improve creditworthiness in an increasingly data-driven financial environment.
Keywords	Peer-to-Peer Lending, Lending Club, Loans, Interest Rate, Credit, Borrower, Grade, Debt, Income, Credit Utilization, Charge-offs, Collections, Credit Line Age, Application Type, Revolving Balance, FICO Score, Logistic Regression
Field	Computer > Data / Information
Published In	Volume 7, Issue 5, September-October 2025
Published On	2025-10-22
DOI	https://doi.org/10.36948/ijfmr.2025.v07i05.58638

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

What Borrower Characteristics Best Predict Loan Approval Probability in Peer-To-Peer Lending Platforms, and How Do These Vary Between Models? How Can Small To Medium-Sized Businesses Ameliorate These Factors?

Share this