Analyzing the findings using the proper data analysis methodologies comes next, after all the necessary information has been gathered and prepared (Albrecht et al., 2006). Finding outliers, trends, divergences from expected behavior, and statistical abnormalities that can point to an increased risk of fraud is the main goal of this stage (ANGGRIANI, 2002). To identify transactions or patterns that vary considerably from typical business activity, analytical techniques including ratio analysis, trend analysis, outlier detection, and statistical testing are frequently employed.

Analysts are able to identify abnormal transaction concentrations, abnormal time fluctuations, or acts that break accepted norms and policies (Audu et al., 2020). Unusual activity may be indicated, for instance, by a sharp increase in vendor payments, frequent transactions at regular quantities, or departures from seasonal patterns. These results help in reducing big datasets into more manageable, high-risk categories that merit further investigation.

It is crucial to understand that not all anomalies are indication of fraud, since unusual trends can also result from normal company operations, data errors, or legitimate business activity (Dumitrescu et al., 2022). However, since purposeful manipulation conflicts with the way data behaves normally, all frauds eventually produce abnormalities. As a result, this step acts as a crucial filter, allowing analysts to concentrate their investigative efforts in areas where fraud risk is highest while retaining professional judgment and skepticism.

References:

  • Albrecht WS, Albrecht CO, Albrecht CC, et al. (2006) Fraud examination: Thomson South-Western New York, NY.
  • ANGGRIANI N. (2002) Analysis of E-government and ICT Policy in Indonesia: Lessons from Comparative Experience: ISS.
  • Audu ARA, Cuzzocrea A, Leung CK, et al. (2020) An Intelligent Predictive Analytics System for Transportation Analytics on Open Data Towards the Development of a Smart City. In: Barolli L, Ikeda M and Hussain FK (eds) Advances in Intelligent Systems and Computing. Springer Verlag, 224-236.
  • Dumitrescu B, Băltoiu A and Budulan Ş. (2022) Anomaly detection in graphs of bank transactions for anti money laundering applications. Ieee Access 10: 47699-47714.