Fraud detection by a multinomial model. Separating honesty from unobserved fraud. A Monte Carlo simulation study (developed)

With the problem of detecting tax evasion in mind, we investigate how to identify items, e.g. individuals or companies, that are wrongly classified as honest. Normally, we observe two groups of items, labeled fradulent and honest, but suspect that many of the observationally honest items are, in fact, fraudulent. The items observed as honest are …

Continue Reading