>> "In contrast, fraudsters tend to create accounts and then go shop for merchandise."
Perhaps this is overreaching and the results have been skewed by various factors. According to one of the tables on that post, the analysis revealed that a purchase occurring between 3-10 minutes of account creation is 'quite suspicious'. I find it hard to believe this matches to reality.
I hope I don't come across as insulting, it's just that I know how easy it is to get false positives with anything involving statistics and machine learning.
These results are averaged across many different types of e-commerce companies. So you're correct that a particular company shouldn't necessarily set up a rule to flag transactions occurring 3-10 mins from account creation.
At Sift Science, a user is flagged based on a combination of many different factors. So while a transaction 3-10 minutes after signup is associated with increased risk of fraud, a user typically has to match many different patterns to be flagged as an overall risk.
2 comments
[ 3.3 ms ] story [ 17.3 ms ] threadPerhaps this is overreaching and the results have been skewed by various factors. According to one of the tables on that post, the analysis revealed that a purchase occurring between 3-10 minutes of account creation is 'quite suspicious'. I find it hard to believe this matches to reality.
I hope I don't come across as insulting, it's just that I know how easy it is to get false positives with anything involving statistics and machine learning.
At Sift Science, a user is flagged based on a combination of many different factors. So while a transaction 3-10 minutes after signup is associated with increased risk of fraud, a user typically has to match many different patterns to be flagged as an overall risk.