Financial misstatements have plagued the financial world for several decades. However they have increased in frequency and affected more stockholders and stakeholders in recent years. This intensity of occurrence has prompted the need for more fraud detecting methods from auditors and government regulators alike. Traditionally, statistical models have been utilized in detecting financial misstatements. However, these statistical models are based on assumptions, such as a log-linear relation among the independent variables, which are not applicable to financial data. Artificial neural networks are not bounded by the limitations affecting statistical models, and have been found to give robust results when applied to classification problems.
The purpose of study was to compare unsupervised neural networks, the Nonlinear Principal Component Analysis (NLPCA) network and the Kohonen Self-Organizing Map (SOM), in detecting financial misstatements. As a performance benchmark, the results from the NLPCA and SOM networks were compared to the traditional statistical method, the logit model.
The dataset used in this study consisted of firms who issued financial statements for the period 1990 to 2005. The dataset was limited to firms from the computer-technology industry and financial services sectors, and whose annual financial statements were publicly available. Using the matched-pair approach, each fraud firm was paired with a similar non-fraud firm based on industry, time period and size.
Unlike the Logit model, the NLPCA and SOM models required the determination of several parameters. The configurations for the NLPCA and SOM models were found experimentally. In order to attain a true comparison between the NLPCA, SOM and Logit models, both training and testing for the models were done with the same samples.
Using different metrics for comparison it was found that the NLPCA and SOM models were effective in detecting financial misstatements. It was also determined that these unsupervised neural networks produced better classification accuracies than the Logit model. Additionally, the NLPCA model, which is based on correlational learning, marginally outperformed the SOM model, which is based on competitive learning. The results from this study support future use of NLPCA and SOM as assessment tools in detecting financial misstatements.