A Neural Network Approach to Estimating the Allowance for Bad Debt

2011 American Accounting Association Mid-Atlantic Regional Meeting, Baltimore, MD

Posted: 27 Jul 2011 Last revised: 2 Jan 2012

See all articles by Donald T. Joyner

Donald T. Joyner

Virginia Commonwealth University

Ruth W. Epps

Virginia Commonwealth University - Department of Accounting

Heinz Roland Weistroffer

Virginia Commonwealth University (VCU) - School of Business

Robert L. Andrews

affiliation not provided to SSRN

Date Written: April 1, 2011

Abstract

Neural network computer systems, which mimic some of the characteristics of the human brain, have been developed and may offer an alternative method for estimating the allowance for bad debt. These systems can predict what events may happen, analyze what did happen, and adjust the factor weights accordingly for the next set of event predictions. Thus, it is noteworthy to explore the use of neural networks to predict what a reasonable allowance for bad debt should be for an entity based on an array of interacting variables. Since, a neural network can incorporate both endogenous and exogenous variables; it is feasible to use such a system to develop a tool which may generate a better estimation of the allowance for bad debt than the traditional approaches.

Our research findings indicate neural networks are better predictors of a company’s ending allowance for bad debt than regression. On a case by case basis, even when neural networks provide a less accurate estimate than regression, statistical analyses show neural networks to be a less volatile method and the predictions less likely to result in significant differences from the actual balance sheet allowance amount.

Keywords: Allowance for bad debt, Bad debt expense, neural networks in accounting

Suggested Citation

Joyner, Donald T. and Epps, Ruth W. and Weistroffer, Heinz Roland and Andrews, Robert L., A Neural Network Approach to Estimating the Allowance for Bad Debt (April 1, 2011). 2011 American Accounting Association Mid-Atlantic Regional Meeting, Baltimore, MD, Available at SSRN: https://ssrn.com/abstract=1888007

Donald T. Joyner

Virginia Commonwealth University ( email )

Richmond, VA 23284
United States

Ruth W. Epps (Contact Author)

Virginia Commonwealth University - Department of Accounting ( email )

301 W Main Street
Richmond, VA 23284-4000
United States

Heinz Roland Weistroffer

Virginia Commonwealth University (VCU) - School of Business ( email )

301 W Main Street
Richmond, VA 23284-4000
United States

Robert L. Andrews

affiliation not provided to SSRN ( email )

Do you have negative results from your research you’d like to share?

Paper statistics

Abstract Views
697
PlumX Metrics