Optimising a bank's credit portfolio

Annshirley Aba Afful, Michael Kofi Asare and Raymond Benjamin Afful

International Journal of Applied Management Science, 2016, vol. 8, issue 1, 68-82

Abstract: The purpose of this paper is to show the practical application of linear programming and logistic regression models in the formulation of an optimal bank credit policy. Firstly, we formulate a linear programming model and develop a solution (using the simplex algorithm) that optimally allocates funds, where a financial institution is facing the problem of allocation of limited funds among different types of loans/advances at different markup/interest rates with varying degree of risk (bad debts). We go further, after optimal allocation of funds, to propose a binary logistic regression model (BLRM) to discriminate loan defaulters from non-defaulters. The study revealed that the available funds of GH¢166 million for credit facilities will yield a return of GH¢35.25 million after allocation. Four important influences were identified and the LR proposed predicts that about 80% of prospective customers are likely not to default.

Keywords: optimisation; bank credit portfolio; loans; optimal fund allocation; linear programming; logistic regression modelling; credit policy; limited funds; credit risk; loan defaults; default risk; financial institutions; banking industry. (search for similar items in EconPapers)
Date: 2016
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=75466 (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:injams:v:8:y:2016:i:1:p:68-82

Access Statistics for this article

More articles in International Journal of Applied Management Science from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().