Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{182079,
        author = {Siddharth Agrawal and Divyansh Jain and Naman Taneja and Dr. Chitra B.T.},
        title = {AI-Powered Credit Scoring for P2P Lending in India: A Research Overview},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {2},
        pages = {780-786},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=182079},
        abstract = {Traditional credit scoring in India struggles to include vast segments of the population who lack formal credit history, leaving many creditworthy individuals underserved. This paper proposes an AI-driven credit scoring system for peer-to-peer (P2P) lending platforms in India, leveraging alternative data sources (such as mobile usage patterns, utility payments, and rent records) to evaluate borrower risk. We survey recent studies showing that machine learning models using such non-traditional data can effectively predict loan default among “credit-invisible” borrowers, thereby improving financial inclusion. We outline a modular system architecture that ingests heterogeneous alternative data, performs feature engineering, and applies AI models (e.g., logistic regression and decision trees) to generate a credit risk score. Using a simulated borrower dataset, we demonstrate model performance via Receiver Operating Characteristic (ROC) curves and Area Under the Curve (AUC) metrics, and we discuss feature importance for interpretability. We also address regulatory compliance (such as Reserve Bank of India’s guidelines for P2P lending and India’s Digital Personal Data Protection Act (DPDP) 2023), ethical considerations like data privacy, bias mitigation, and explainability, as well as intellectual property (IP) implications of AI scoring innovations. The results indicate that AI-powered credit scoring can broaden access to credit for underserved populations while maintaining prudent risk management, if transparency, fairness, and robust data protections are in place.},
        keywords = {AI credit scoring, peer-to-peer lending, alternative data, financial inclusion, machine learning, credit risk assessment, fintech, P2P lending, credit invisibles.},
        month = {July},
        }