Using Machine Learning to Support Peer-to-Peer Loan Funding Decision Support

This study investigates the application of artificial intelligence (AI), specifically machine learning (ML) techniques, in enhancing decision-making processes on peer-to-peer (P2P) lending platforms.Traditional financial institutions use AI in their decision-making processes.However, the use of AI in supporting investor decisions in decentralized P2P environments remains limited.This research addresses a critical inefficiency in the P2P lending process, where creditworthy loan applications approved by platforms often go unfunded by investors, by developing a second-tier decision support model.Using historical data from the Prosper platform, multiple ML models, including Logistic Regression, Support Vector Machines, Neural Networks, and Random Forests, were evaluated for their ability to predict unfundable loans.Findings indicate that AI-powered models can significantly improve funding decision accuracy and reduce investor burden.Random Forest demonstrated the highest suitability among the models assessed across multiple evaluation metrics.These results highlight the potential of AI to enhance the efficiency and reliability of alternative lending ecosystems.