THE IMPACT OF CASH FLOW ON BUSINESS FAILURE ANALYSIS AND PREDICTION

Abdelkader Mazouz
Keenan Crane
Hamdan Bin Mohamed University, Dubai, UAE

Patrick A. Gambrel
U.S. Naval Postgraduate School, CA, USA

ABSTRACT

The purpose of this study is to determine whether cash flow impacts business failure prediction using a neural network. Using a matched sample of 114 failed and 114 non-failed manufacturing firms selected from the Compustat database, accrual-based and cash flow-based neural network models were developed utilizing financial ratios as input variables. A Z-test was performed to test for significance of any difference at the 0.05 level between the classification results of the two models. The accrual-based model correctly classified 92.55% of firms overall in a training sample and 77.5% of firms overall in a holdout sample. The cash flow-based model correctly classified 94.15% of firms overall in a training sample and 82.5% of firms overall in a holdout sample. While the cash flow-based neural network model outperformed the accrual-based neural network model, results of the Z-test revealed that the difference in classification accuracies between the two models was not significant. This study does not provide evidence that cash flow improves business failure prediction.

Full Text PDF Format