E-commerce directors and their IT security and loss prevention counterparts play an endless cat-and-mouse game with cyberthieves. The trick to getting ahead of fraud is anticipating which customers are the most likely thieves, typically through some form of pattern or attribute recognition. The problem is that smart bad guys can change their patterns and attributes as quickly as the good guys learn to recognize them.

The people over at security vendor Simility have looked at the latest patterns and noticed some interesting things (while acknowledging that the patterns won’t necessarily persist for long).

Here is how Simility described its methodology: “We aggregated more than 100 different signals across 500,000 real world browser-based devices throughout January 2016. We looked for patterns in the 10,000 (or 2 percent) of those devices that were in the hands of fraudsters and contrasted those with the other 98 percent of devices in the hands of good or ‘organic’ users.”

To read this article in full or to leave a comment, please click here