Forensic Analytics, 2nd Edition

CHAPTER 11Identifying Anomalies In Time-Series Data

A TIME-SERIES IS AN ORDERED sequence of the successive values of a series of data points, in units or dollars, over equally spaced time intervals. A time-series analysis extrapolates the past series of data points into the future. To extrapolate means to extend the curve beyond the known values in a way that makes sense. In a forensic accounting context, we would then compare our actual results to those predictions. Large deviations from the predictions signal a change in conditions which might include fraud or errors. Time-series analysis is well-suited to forensic analytics because accounting transactions almost always include a time or date stamp. The usual objectives of a time-series analysis are to give the forensic accountant, or the auditor, a better understanding of the revenues or expenditures under investigation and to predict the revenues or expenses for future periods. These predicted values will be compared to the actual results and significant differences should be reviewed.

The comparison of the actual to the predicted results fits in well with a continuous monitoring environment. Time-series analysis has been made easier to use over the past few years by user-friendly software and the increased computing power of personal computers. One issue with accountants running time-series analyses is that the diagnostic statistics are complex, and this might make some people unsure about what the “correct” conclusion ...