Computer-assisted audit techniques based on an enhanced rough set model

Due to the uncertainty of the business environment and critical competition, financial statement fraud (FSF) risk is higher than in past decades. Most FSF is caused by top managers who have the authority to override the internal controls and deploy de facto power against audit committees. An auditor is the last line of defense to detect FSF. Unfortunately, many auditors lack the expertise and experience to deal with related risks. In recent years, with the development of information technology, FSF began to appear and grow rapidly in the embarrassing background of abundant data and poor knowledge. Rough Set Theory (RST) is an emerging technique to deal with the related problems in data mining and knowledge acquisition. However, the RST approach has not been extensively explored in the field of auditing. This investigation developed an enhanced RST (ERST) model, which employs classification and regression tree (CART) to determine a reduct of RST, and analyzed the audit related risks in audit procedure in Taiwan. The experiment results showed that the ERST model select crucial information from data without predetermining factor and can provide accurate rates for inference rules. The auditors can employ ERST as computer-assisted audit techniques to apply it to scan financial statement posted on Internet Websites and analyze the difference between trends of the company's report. In addition, ERST model provides a decision rules base for auditors to save time and costs in limited auditing procedure. Hence, the developed ERST model is a promising alternative for detecting financial statement fraud.