Analysis of the Characteristics of Different Peer-To-Peer Risky Loans

Bih Huang Jin*, Yung Ming Li, Kuan Te Ho

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This study analyzes data from Lending Club 2011 January to 2016 January. We use survival analysis and proportional hazards model to find what loan characteristics will have lower default rate in high-risk group and low risk group. The grouping way is through the lending Club credit score. Our study provides a way to analyze loan characteristics to reduce information asymmetry and default rate. To earn higher interest and take the principal back have always been the biggest issue in the financial world. Our research gives the advices through survival analysis with empirical data. The results show the repayment characteristics of the high-risk group and the low-risk group is similar. Except for the following four characteristics, ‘mortgage’, ‘education’, ‘home improvement’, and ‘medical’ are opposite.

Original languageEnglish
Title of host publicationInformation Systems and Technologies - WorldCIST 2023
EditorsAlvaro Rocha, Hojjat Adeli, Gintautas Dzemyda, Fernando Moreira, Valentina Colla
PublisherSpringer Science and Business Media Deutschland GmbH
Pages97-105
Number of pages9
ISBN (Print)9783031456411
DOIs
StatePublished - 2024
Event11th World Conference on Information Systems and Technologies, WorldCIST 2023 - Pisa, Italy
Duration: 4 Apr 20236 Apr 2023

Publication series

NameLecture Notes in Networks and Systems
Volume799 LNNS
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

Conference11th World Conference on Information Systems and Technologies, WorldCIST 2023
Country/TerritoryItaly
CityPisa
Period4/04/236/04/23

Keywords

  • Data Analysis
  • FinTech
  • Loan Risk
  • P2P Lending

Fingerprint

Dive into the research topics of 'Analysis of the Characteristics of Different Peer-To-Peer Risky Loans'. Together they form a unique fingerprint.

Cite this