Logistic Regression Analysis Of Predictors Of Loan Defaults By Customers Of Non-Traditional Banks In Ghana

  • Edinam Agbemava Department of Accountancy, Ho Polytechnic, Ghana
  • Israel Kofi Nyarko Department of Marketing, Ho Polytechnic, Ghana
  • Thomas Clarkson Adade Department of Accountancy, Ho Polytechnic, Ghana
  • Albert K. Bediako Department of Accountancy, Ho Polytechnic, Ghana

Abstract

The objective of this research is to identify the risk factors that influence loan defaults by customers in the microfinance sector and to develop a model that links these factors to credit default by customers in the sector. Data from a microfinance institution based in Accra Ghana was used. A binomial logistic regression analysis was fitted to a data of 548 customers who were granted credit from January 2013 to December 2014. The results of the study revealed that six factors: X3 (Marital Status); X7 (Dependents); X11 (Type of Collateral or Security); X13(Assessment); X15 (Duration); and X16 (Loan Type) were statistically significant in the prediction of loan default payment with a predicted default rate of 86.67%. It is therefore suggested that microfinance institutions adopt among others, the default risk model to ascertain the level of risk since it’s relatively efficient and cost effective. There should also be up to date training for loan officers of microfinance institutions in order to improve on their assessment skills and methodology. The supervising body of microfinance institutions (Bank of Ghana) should also consider enacting laws that will ensure that all such institutions in Ghana are roped into centralized database to check multiple borrowing and also serve as an internal control measure for the sustainability of these institutions.

Downloads

Download data is not yet available.
Published
2016-01-29
How to Cite
Agbemava, E., Nyarko, I. K., Adade, T. C., & Bediako, A. K. (2016). Logistic Regression Analysis Of Predictors Of Loan Defaults By Customers Of Non-Traditional Banks In Ghana. European Scientific Journal, ESJ, 12(1), 175. https://doi.org/10.19044/esj.2016.v12n1p175