KNUSTSpace >
Theses / Dissertations >
College of Science >

Please use this identifier to cite or link to this item: http://hdl.handle.net/123456789/10031

Title: Prediction of loan default using logistic regression: A case study of Ahafo Ano Premier Rural Bank
Authors: Adu-Gyamfi, Franklin
Issue Date: 20-Jan-2017
Abstract: Advancement of loan facilities among Rural banks to individuals and Small and Medium Enterprises (SMEs) is associated with high risk due to default in re- payment of such loan facilities in Ghana.This study seeks to explore the characteristics of customers of the Ahafo Ano Rural Bank that make them more likely to default in loan repayment. Loans form the major part of the assets of banks in Ghana. Loans are the main source of income for these banks which also intends to be very risky to the lender. Rural banks have its constituency in the lending activity of rural folks in Ghana which were set up by Government of Ghana Banking policy.Logistic regression was applied to customer loan application data from Ahafo Ano Premier Rural Bank to determine characteristics of customers who default (dependent variable) with demographic and socio - economic factors as independent variables . A total of 152 customers were con- sidered for the study. Preliminary analysis by the use of test of independence identifi ed, loan type (commercial and susu), marital status (married) from the Chi - Square statistic. Logistic regression obtained from the study had type of loan (commercial), loan repayment period cum number of dependents of customer been statistically signifi cant (p 􀀀 values < 0:5). The model obtained is: Log(Odds) = 3:863X1 + 0:088X2 􀀀 0:234X3. In conclusion, the study fi ndings show that customers with more months to pay a loan, married customers, and customers with smaller number of dependents are more likely to default. Results and fi ndings from the study will help the bank and other financial institutions to make informed decisions by identifying low risk and high risk customers when granting loans to their customers.
Description: A thesis submitted to the Department of Mathematics and Statistics, Kwame Nkrumah University of Science and Technology in partial fulfillment of the requirement for the Degree of Master of Science in Industrial Mathematics, 2016
URI: http://hdl.handle.net/123456789/10031
Appears in Collections:College of Science

Files in This Item:

File Description SizeFormat
FRANKLIN ADU-GYAMFI.pdf416.78 kBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


Valid XHTML 1.0! DSpace Software Copyright © 2002-2010  Duraspace - Feedback