Fraud

==Detection==
{{further|Data analysis techniques for fraud detection}}
[[File:White Van Speaker Scam fraudulent MSRP.jpg|thumb|A fraudulent manufacturer's suggested retail price on a speaker]]
The detection of fraudulent activities on a large scale is possible with the harvesting of massive amounts of financial [[data analysis|data]] paired with [[predictive analytics#Fraud detection|predictive analytics]] or forensic analytics, the use of electronic data to reconstruct or detect financial fraud.

Using computer-based analytic methods in particular allows for surfacing of errors, anomalies, inefficiencies, irregularities, and biases which often refer to fraudsters gravitating to certain dollar amounts to get past internal control thresholds.<ref>{{cite journal|title=Forensic Analytics|url=http://www.analytics-magazine.org/july-august-2013/835-forensic-analytics |first1=Priti |last1=Ravi |website=Analytics Magazine|date=July–August 2013|access-date=8 November 2023|archive-date=19 August 2014|archive-url=https://web.archive.org/web/20140819083330/http://www.analytics-magazine.org/july-august-2013/835-forensic-analytics|url-status=dead }}</ref> These high-level tests include tests related to Benford's Law and possibly also those statistics known as descriptive statistics. High-level 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.<ref>{{Cite web|title=Using Data Analysis to Detect Frauds|url=https://www.acfe.com/uploadedFiles/ACFE_Website/Content/review/da/04-Advanced-Data-Analysis-Techniques.pdf|access-date=5 July 2020|publisher=Association of Certified Fraud Examiners|archive-date=5 July 2020|archive-url=https://web.archive.org/web/20200705210612/https://www.acfe.com/uploadedFiles/ACFE_Website/Content/review/da/04-Advanced-Data-Analysis-Techniques.pdf|url-status=dead}}</ref>