Harlan L. Etheridge

A Comparison of Selected Artificial Neural Networks that Help Auditors Evaluate Client Financial Viability

This study compares the performance of three artificial neural network (ANN) approaches—backpropagalion, categorical learning, and probabilistic neural network—as classification tools to assist and support auditors judgment about a clients continued financial viability into the future (going concern status). ANN performance is compared on the basis of overall error rates and estimated relative costs of misclassificaticn (incorrectly classifying an insolvent firm as solvent versus classifying a solvent firm as insolvent). When only the overall error rate is considered, the probabilistic neural network is the most reliable in classification, followed by backpropagation and categorical learning network. When the estimated relative costs of misclassification are considered, the categorical learning network is the least costly, followed by backpropagation and probabilistic neural network.

A comparison of the relative costs of financial distress models: artificial neural networks, logit and multivariate discriminant analysis

This study uses two artificial neural networks (ANNs), categorical learning/instar ANNs and probabilistic (PNN) ANNs, suitable for classification and prediction type issues, and compares them to traditional multivariate discriminant analysis (MDA) and logit to examine financial distress one to three years prior to failure. The results indicate that traditional MDA and logit perform best with the lowest overall error rates. However, when the relative error costs are considered, the ANNs perform better than traditional logit or MDA. Also, as the time period moves farther away from the eventual failure date, ANNs perform more accurately and with lower relative error costs than logit or MDA. This supports the conclusion that for auditors and other evaluators interested in early warning techniques, categorical learning network and probabilistic ANNs would be useful.

Improving Decision Effectiveness of Artificial Neural Networks: A Modified Genetic Algorithm Approach

This study proposes the use of a modified genetic algorithm (MGA), a global search technique, as a training method to improve generalizability and to identify relevant inputs in a neural network (NN) model. Generalizability refers to the NN models ability to perform well on exemplars (observations) that were not used during training (out-of-sample); improved generalizability enhances NNs acceptability as a valid decision-support tool. The MGA improves generalizability by setting unnecessary weights (or connections) to zero and by eliminating these weights. Because the eliminated weights have no further impact on the training (in-sample or out-of-sample data), the relevant variables can be identified from the model. By eliminating unnecessary weights, the MGA is able to search and find a parsimonious model that generalizes well. Unlike the traditional NN, the MGA identifies the model variables that contribute to an outcome, helping decision makers to rationalize output and accept results with greater confidence. The study uses real-life data to demonstrate the use of MGA.

E-Business Education at AACSB-Affiliated Business Schools: A Survey of Programs and Curricula

Abstract Business schools throughout the United States and abroad have responded to the explosion in electronic business (e-business) by offering programs in e-business. In this study, we examined 77 e-business programs at AACSB-affiliated business colleges and found four basic types: the master of science (MS), bachelor of science (BS), and nondegree certificate (NDC) in e-business, and the master in business administration (MBA) with a specialization or concentration in e-business. MBA programs were the most numerous. The most commonly offered e-business courses were E-Business Marketing in the MBA, MS, and NDC programs, and Introduction to E-Business in the BS programs. In this article, we provide further information on the e-business programs examined.

An investigation of the impact of financial viability model selection on audit costs: logit, multivariate discriminant analysis and artificial neural networks

The purpose of this paper is twofold. Firstly, we provide evidence that relying on Type I, Type II and overall error rates to select a model for analysing the financial health of audit clients can result in greater costs than using our alternative approach. Secondly, we show that auditors who use an artificial neural network (ANN) as a tool to analyse the financial viability of audit clients need to consider the underlying ANN paradigm before developing a model in order to minimise audit costs. Our results show that a categorical learning neural network (CLN) minimises the overall cost associated with the auditor examination of audit client financial health. This ANN outperforms both statistical techniques and other ANN paradigms. Consequently, auditors who wish to minimise the total costs associated with their audits should use a CLN or similar type of ANN when assessing audit client financial health.