（2006）Continuous Assurance Using Text Mining.pdfVIP

C O N T I N U O U S A S S U R A N C E U S I N G T E X T M I N I N G Glen L. Gray College of Business and Economics California State University at Northridge glen.gray@ Roger Debreceny School of Accountancy Shidler College of Business University of Hawai`i at Mānoa roger@ DRAFT ONLY – DO NOT CITE Comments welcome. 23 October 2006 C O N T I N U O U S A S S U R A N C E U S I N G T E X T M I N I N G ABSTRACT Three levels of continuous assurance can be delineated, from continuous monitoring over business processes at the lowest level to continuous audit of corporate performance at the highest level. A number of research projects and commercial software products address monitoring of business processes. These projects include a variety of monitors that can be grouped under the general rubric of embedded audit modules. These modules normally are designed to monitor events and controls within accounting information systems and transaction processing subsystems such as sales systems. However, much of the information that is relevant to continuous monitoring of business processes takes place outside the accounting information system. It may be difficult, for example, to tease out evidence of questionable related party arrangements or inappropriate revenue recognition by monitoring transactions and accounting info