Financial fraud detection using vocal, linguistic and financial cues

a r t i c l e i n f o Corporate financial fraud has a severe negative impact on investors and the capital market in general. The current resources committed to financial fraud detection (FFD), however, are insufficient to identify all occurrences in a timely fashion. Methods for automating FFD have mainly relied on financial statistics, although some recent research has suggested that linguistic or vocal cues may also be useful indicators of deception. Tools based on financial numbers, linguistic behavior, and non-verbal vocal cues have each demonstrated the potential for detecting financial fraud. However, the performance of these tools continues to be poorer than desired, limiting their use on a stand-alone basis to help identify companies for further investigation. The hypothesis investigated in this study is that an improved tool could be developed if specific attributes from these feature categories were analyzed concurrently. Combining features across categories provided better fraud detection than was achieved by any of the feature categories alone. However, performance improvements were only observed if feature selection was used suggesting that it is important to discard non-informative features. Efficient allocation of capital is critical to stimulate economic growth, the engine that drives improvements in social welfare. The financial world has been rocked by a wave of accounting scandals, from Enron and WorldCom in the early 2000s to the collapse of Lehman Brothers in 2008 leading to a significant degradation of trust in capital markets and concomitant inefficient capital allocation decisions. In order to restore trust in the capital markets, regulators have passed a series of reforms, such as the Sarbanes Oxley Act that impose penalties on those who commit financial misdeeds. However, such penalties will be a helpful deterrent if and only if frauds are detected in a timely fashion. The current resources committed to fraud detection by the Securities and Exchange Commission (the regulatory body that oversees capital markets in the United States) are insufficient to identify all occurrences of frauds in a timely fashion. Moreover, the Center for Audit Quality, which serves the financial auditing profession, recently called for the identification of new ways to better detect financial fraud so as to restore investor confidence [31]. Thus, an automated method for accurate financial fraud detection (FFD) has the potential to deter financial misdeeds and stabilize capital markets. Most corporate FFD methods documented in accounting and finance research have focused on financial information (see …