Fraud Detection
For detection of fraudulent activities on the large scale, massive use of (online) data analysis is required, in particular predictive analytics or forensic analytics. Forensic analytics is the use of electronic data to reconstruct or detect financial fraud. The steps in the process are data collection, data preparation, data analysis, and the preparation of a report and possibly a presentation of the results. Using computer-based analytic methods Nigrini's wider goal is the detection of fraud, errors, anomalies, inefficiencies, and biases which refer to people gravitating to certain dollar amounts to get past internal control thresholds. The analytic tests usually start with high-level data overview tests to spot highly significant irregularities. In a recent purchasing card application these tests identified a purchasing card transaction for 3,000,000 Costa Rica Colons. This was neither a fraud nor an error, but it was a highly unusual amount for a purchasing card transaction. These high-level tests include tests related to Benford's Law and possibly also those statistics known as descriptive statistics. These high-tests are always followed by more focused tests to look for small samples of highly irregular transactions. The familiar methods of correlation and time-series analysis can also be used to detect fraud and other irregularities. Forensic analytics also includes the use of a fraud risk-scoring model to identify high risk forensic units (customers, employees, locations, insurance claims and so on). Forensic analytics also includes suggested tests to identify financial statement irregularities, but the general rule is that analytic methods alone are not too successful at detecting financial statement fraud.
Read more about this topic: Fraud