Predicting loan repayment default among second tier borrowers in Ghana

Kwami Adanu and Emma Boateng

International Journal of Entrepreneurship and Small Business, 2015, vol. 24, issue 3, 417-432

Abstract: This paper evaluates factors that affect the probability of loan repayment defaults using repayment data on loans granted by Snapi Aba Savings and Loans Ltd, Ghana. Results from logistic regression analysis of the data indicate that, contrary to findings elsewhere, age of borrowers is irrelevant in predicting probability of defaults in this study. Rather, credit screenings should focus on the gender of borrowers, payment frequency, loan cycle, and loan size. The probability of repayment defaults increases by about 1.3% for male borrowers as compared to female borrowers. Further, clients with longer credit history with the lending agency are more likely to default, and default probability is declining in loan size. Also, one-time lump-sum loan repayments reduce repayment defaults by about 2.2% as compared to regular monthly repayment options. Finally, educational level of borrowers and interest rates are irrelevant in predicting defaults.

Keywords: microfinance; logit; loans; small and medium-sized enterprises; SMEs; default prediction; loan repayments; repayment default; loan defaults; second tier borrowers; Ghana; credit screening; gender; payment frequency; loan cycle; loan size. (search for similar items in EconPapers)
Date: 2015
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.inderscience.com/link.php?id=67466 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ids:ijesbu:v:24:y:2015:i:3:p:417-432

Access Statistics for this article

More articles in International Journal of Entrepreneurship and Small Business from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().