CEC Theses and Dissertations

Title

A Comparative Analysis of DDs and Humans on Making Loan Decisions

Date of Award

2002

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Graduate School of Computer and Information Sciences

Advisor

Michael J. Laszlo

Committee Member

Sumitra Mukherjee

Committee Member

Junping Sun

Abstract

Decision support systems have long been contemplated as an alternative to, or at least an adjunct to, human decision making in the loan approval process. In this study, the author compared decision support systems to human decision-making with respect to consistency and accuracy in the loan approval assessment. Sample loan files were from a Federal Credit Union at which the author worked. The decision support system was written in Turbo Basic. The system was programmed to determine if a loan should be accepted or rejected. Loan officers were required to enter financial and property information from each application into the program. Both the human and decision support system either accepted or rejected each application. If the application was rejected, each gave the reason for rejection. The results were compared for consistency and accuracy. For this study, consistency relates to the uniformity and reliability of decisions. Accuracy relates to the correctness of decisions determined by the currency or default status of the loans. The ultimate objective of this study was to show the feasibility of using a decision support system as a tool in the loan approval process. The null hypothesis of the study was that there is no significant difference in the accuracy and consistency of loan decisions made by human experts and decision support systems. This study indicated that although there were differences in the decisions, the decisions were not significantly different. It did not matter which system was used to make the decision, it took less of the loan officer's time when using the decision support system as a tool.

This document is currently not available here.

  Link to NovaCat

Share

COinS