A Comparative Study of Machine Learning Models for Default Groups Clustering and Credit Scoring Prediction for Peer-to-peer Lending

Linked Agent
Hewahi, Nabil Mahmood , Thesis advisor
Language
English
Extent
[1], 12, 110, [10] Pages
Place of institution
Sakhir, Bahrain
Thesis Type
Theses (Master)
Institution
"University of Bahrain, College of Science Environmental and Sustainable Development program
English Abstract
Abstract: With the intervention of financial technology (FinTech), peer-to-peer (P2P) lending platforms have emerged as a disruptive force in the financial sector, directly connecting borrowers with lenders without the need for traditional intermediaries or collateral. P2P lending platforms heavily depend on the accuracy of creditworthiness predictions for borrowers through assessing the credit risk involved in lending. Machine Learning (ML) models provide the opportunity to improve credit scoring predictions and boost the overall efficiency and sustainability of P2P platforms.
Member of
Identifier
https://digitalrepository.uob.edu.bh/id/804eef4e-6e3a-46c7-9826-5f7df5f495b3