Credit-Risk Assessment of Small Business Loans using Naïve Bayes, Decision Tree and Random Forest

Ahmed, Anisa Nizar (2019) Credit-Risk Assessment of Small Business Loans using Naïve Bayes, Decision Tree and Random Forest. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (848kB) | Preview

Abstract

Small and medium-sized enterprises are the backbone of a country’s economy, providing employment to majority of the working population and contributing immensely towards Gross Domestic product (GDP). However, due to the their limited amount of resources and budget, small businesses loans often get rejected by banks who are hesitant to lend due to high credit-risk. The aim of this study is to analyse small business loan applications using machine learning algorithms for identifying factors that lead to high credit-risk. Machine learning can provide a transparent and efficient way of assessing credit-risk than the traditional banking models. Naïve Bayes, Random Forest and Decision Tree are implemented and compared in terms of accuracy. It is seen that interest rate charged by the bank has the highest impact on credit-risk with loans less than 15% annual interest rate having the least credit-risk.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software Q Science > QA Mathematics > Electronic computers. Computer science > Computer Systems T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science > Computer Systems H Social Sciences > HG Finance > Credit. Debt. Loans.
Divisions:	School of Computing > Master of Science in FinTech
Depositing User:	Dan English
Date Deposited:	02 Jun 2020 11:54
Last Modified:	02 Jun 2020 11:54
URI:	https://norma.ncirl.ie/id/eprint/4220

Actions (login required)

View Item