These articles always seem to imply that you can use those traits for detection. Can you? I mean, the numbers and wording imply that you can, but some of the stats are not very clear or intuitive.

For example, just because group X usually doesn't eat lunch doesn't mean that not eating lunch is a good trait to detect them in the general population.

Also, 6% of outlook.com is used for fraud? This is a huge percentage.

How does this company detect multiple accounts on the device?