A 177 Category: Networking & Telecommunication Application of Fuzzy Logic to Fraud Detection Mary Jane Lenard University of North Carolina – Greensboro, USA Pervaiz Alam Kent State University, USA INTRODUCTION In light of recent reporting of the failures of some of the major publicly-held companies in the U.S. (e.g., Enron & WorldCom), it has become increasingly important that management, auditors, analysts, and regulators be able to assess and identify fraudulent inancial reporting. The Enron and WorldCom failures illustrate that inancial reporting fraud could have disastrous consequences both for stock- holders and employees. These recent failures have not only adversely affected the U.S. accounting profession but have also raised serious questions about the credibility of inancial statements. KPMG (2003) reports seven broad categories of fraud experienced by U.S. businesses and governments: employee fraud (60%), consumer fraud (32%), third-party fraud (25%), computer crime (18%), misconduct (15%), medical/insurance fraud (12%), and inancial reporting fraud (7%). Even though it occurred with least frequency, the average cost of inancial reporting fraud was the highest, at $257 million, followed by the cost of medical/insurance fraud (average cost of $33.7 million). Statistical methods, expert reasoning, and data mining may be used to achieve the objective of identifying inancial reporting fraud. One way that a company can justify its i- nancial health is by developing a database of inancial and non-inancial variables to evaluate the risk of fraud. These variables may help determine if the company has reached a stress level susceptible to fraud, or the variables may identify fraud indicators. There are a number of methods of analysis that may be used in fraud determination. Fuzzy logic is one method of analyzing inancial and non-inancial statement data. When applied to fraud detection, a fuzzy logic program clusters the information into various fraud risk categories. The clusters identify variables that are used as input in a statistical model. Expert reasoning is then ap- plied to interpret the responses to questions about inancial and non-inancial conditions that may indicate fraud. The responses provide information for variables that can be developed continuously over the life of the company. This article summarizes the speciics of fraud detection modeling and presents the features and critical issues of fuzzy logic when applied for that purpose. BACKGROUND Fraud Detection The problem of fraudulent inancial reporting is not limited to the U.S. In 2002, the Dutch retailer, Ahold, disclosed losses of $500 million related to accounting at its U.S. subsidiary (Arnold, 2003). Recently, Parmalat, an Italian irm, declared insolvency as a result of fraudulent inancial reporting. The CEO of Parmalat has been accused of mishandling $10 billion and of hiding losses in offshore funds and bank accounts. The scandal at Parmalat could also have serious consequences for the company’s auditor (Gallani & Troimov, 2004). The auditor’s responsibility for fraud detection in the U.S. has been deined in Statement on Auditing Standards No. 99, Fraud Detection in a GAAS Audit (AICPA, 2002). This statement has four key provisions (Lanza, 2002): (1) increased emphasis on professional skepticism, (2) frequent discussion among audit team personnel regarding the risk of misstatement due to fraud, (3) random audit testing of locations, accounts, and balances, and (4) procedures to test for management override of controls. Auditors are discour- aged from placing too much reliance on client representation and are required to maintain a skeptical attitude throughout the audit. The standard encourages auditors to engage in frequent discussion among engagement personnel regarding the risk of material misstatement due to fraud. SAS 99 also requires auditors to inquire of management and others not directly involved with fraud, perform analytical procedures, and conduct necessary tests to assess management override of controls. Finally, auditors are advised to evaluate the risk of fraud and steps taken by the client to mitigate the risk of fraud. The U.S. Congress in 2002 passed the Sarbanes-Oxley Act, which spells out a number of steps irms must take to minimize fraudulent inancial reporting. This legislation requires the principal executive oficer and the principal inancial oficer of publicly traded companies to certify the appropriateness of the inancial statements and disclosures in each quarterly and annual report that their company is- sues. These oficers are also responsible for establishing and maintaining internal controls within the company. Further, they must disclose to auditors and the audit committee of Copyright © 2009, IGI Global, distributing in print or electronic forms without written permission of IGI Global is prohibited.