An International Meeting of the American Accounting Association American Accounting Association 2006 Annual Meeting August 6–9, 2006 Washington, D.C.

Michael Alles
Rutgers University

Alexander Kogan
Rutgers University

Miklos Vasarhelyi
Rutgers University

Jia Wu
University of Massachusetts – Dartmouth

Abstract: Our objective is the development and empirical evaluation of a new analytical methodology of Continuity Equations (CE), stable probabilistic relationships between disaggregated Business Process (BP) metrics. CEs can be utilized in Continuous Auditing (CA) as expectation models to calculate the expected values of BP metrics, as well as the acceptable levels of variance. The deviation of the observed BP metric value beyond the acceptable range represents an anomaly to be investigated further by the auditors. We design a set of online learning and error correction protocols for automatic model inference and updating. Our results indicate that the CE models have good prediction accuracy and error correction improves performance. We demonstrate the superiority of the Multivariate Time Series Model in successfully identifying significant seeded errors, and it is possible to identify significant business process problems sooner, and potentially at a lower cost.

Back to Session Listing

AAA Home Page