Auditing Journal Entries Using Extreme Value Theory

The area of journal entries is deemed to pose a high risk of material misstatements to financial statements. The paper defines “suspicious” journal entries as having both a large monetary amount and a low probability of occurring. ” Suspicious’ journal entries are rare and have a monetary amount that is large enough to materially misstate financial statements. The Bayesian analysis allows auditors to update their expectations concerning “suspicious” Journal entries given new data as well as transfer their knowledge from an audit engagement to the next. Section 6 draws conclusions and suggests possible directions for further research.

Auto112

https://aisel.aisnet.org/cgi/viewcontent.cgi?article=1392&context=ecis2013_cr

Machine Learning with Python

NLU Training Data – Github