Credit Risk Assessment in P2P Lending Using LightGBM and Particle Swarm Optimization

Yosza Dasril, Yosza Dasril and Muslim, Much Aziz and Al Hakim, M. Faris and Jumanto, Jumanto and Budi Prasetiyo, Budi Prasetiyo (2023) Credit Risk Assessment in P2P Lending Using LightGBM and Particle Swarm Optimization. Register, 9 (1). pp. 18-28. ISSN 2502-3357

Text J15898_e63681e26a66ff10c518c7ea4a580069.pdf Restricted to Registered users only Download (800kB) | Request a copy

Abstract

Credit risk evaluation is a vital task in the P2P Lending platform. An effective credit risk assessment method in a P2P lending platform can significantly influence investors' decisions. Machine learning algorithm such as LightGBM can be used to evaluate credit risk. However, the results in evaluating P2P lending need to be improved. This research aims to improve the accuracy of the LightGBM algorithm by combining it with the Particle Swarm Optimization (PSO) algorithm. This research is novel as it combines LightGBM with PSO for large data from the Lending Club Dataset, which can be accessed on Kaggle.com. The highest accuracy also presented satisfactory results with 98.094% accuracy, 90.514% Recall, and 97.754% NPV, respectively. The combination of LightGBM and PSO has resulted in better outcome.

Item Type:	Article
Uncontrolled Keywords:	LightGBM, PSO, Credit Risk Assessment, P2P Lending Machine Learning
Subjects:	T Technology > T Technology (General)
Divisions:	Faculty of Technology Management and Business > FPTP
Depositing User:	Mr. Mohamad Zulkhibri Rahmad
Date Deposited:	30 Jul 2024 03:13
Last Modified:	30 Jul 2024 03:13
URI:	http://eprints.uthm.edu.my/id/eprint/11442

Actions (login required)

View Item