Hacker News new | comments | show | ask | jobs | submit login

Benfords law is instrumental in fraud detection, the Enron guys were wise to it, but Bernie Madoff was not:


As a friend of mine pointed out, how is this possible? Shouldn't fraudulent numbers also follow Benford's law?

If you are aware of it, you make sure your fake data follows Benford's law. Otherwise, your fake data will be 'random', because people assume that is how it is supposed to look.

Random data doesn't follow the law. Fraudulent tax returns are essentially random numbers, hence, detectable.

Uniformly distributed random data doesn't follow the law. Data whose logarithm is uniformly distributed does.

Guidelines | FAQ | Support | API | Security | Lists | Bookmarklet | Legal | Apply to YC | Contact