Abstract

This study demonstrates a comprehensive framework for financial credit-risk analysis in the context of peer-to-peer (P2P) lending, which is a rapidly expanding industry that enables people to lend and borrow money not using conventional financial institutions. However, the considerable default risk associated with P2P lending shows serious difficulties for investors. Difficulties can be overcome through a framework based on feature selection and data discretization approaches for mining association rules from P2P lending data. Providing useful information for credit-risk analysis in P2P lending, obtained association rules can be used to identify trends and connections in the data that indicate a borrower’s creditworthiness and likelihood of payback.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call