（2009）The Implications of Unconstrained Data Availability and Aggregation Choice on Continuous Auditing Procedures.pdfVIP

The Implications of Unconstrained Data Availability and Aggregation Choice on Continuous Auditing Procedures Abstract: In this paper we develop a continuous data level auditing system utilizing business process based analytical procedures as a means of investigating how auditing will change in the face of unconstrained data availability and aggregation choice. The first component of the system is automatic transaction verification to filter out exceptions, which are transactions violating user defined business process rules. The second component of the CA system uses continuity equations as benchmarks for process level AP tests which are applied to the verified transaction stream to identify statistical anomalies possibly indicating business process problems. An important innovation in the proposed architecture of the CA system is the utilization of analytical monitoring as the second stage of data analysis rather than the first one. We then evaluate four expectation models that can serve as CE audit benchmarks: a Linear Regression Model, a Simultaneous Equation Model, a Vector Autoregressive model, and a GARCH model. We examine the impact of the choice of the level of data aggregation on anomaly detection performance, and design a set of online learning and error correction protocols for automatic model inference and updating. We evaluate the system’s performance using transaction records of a large healthcare management firm. With a seeded error simulation approach we demonstrate that the use of business process data allows the detection of anomalies that slip through the analytical procedures applied to more aggregated data. Furthermore, the results indicate that under most circumstances the use of real time error correction results in super