Striking a Balance: Evaluating Credit Risk with Traditional and Machine Learning Models

Abstract

This research assesses machine learning models' validity, clarity, and equity, compared to classical models and especially logistic regression in credit risk evaluation. In the traditional model of data management, efficiency and the accuracy of information are challenges; an issue of machine learning models is model selection and multicollinearity. The study intends to help financial institutions establish the best strategy for their needs. Furthermore, it delves into the effect of heterogeneous data sources on the credit risk model using machine learning. The research analyses the implications of using machine learning in assessing credit risk. Interestingly, focusing on peer-to-peer lending platforms, the research aims to deal with the need for more attention to combining machine learning and traditional models in the literature. The deductive method is the application of inferential analyses, the Traditional model is logistic regression, and the Machine Learning model is a neural network (CNN model) based on secondary data from the Kaggle peer-to-peer lending dataset. With likely findings expected to comprise prediction of the probability of default and better availability of loans, risk analysis leads to formulated lending decisions managing a financial portfolio.