@stripe Radar is awesome. Keep up the good work!
-
-
Replying to @windscribecom @stripe
Would be great if you could auto-generate rules based on previous fraud history that would have caught the fraud in the first place
1 reply 0 retweets 0 likes -
Replying to @windscribecom
I can see how that would be useful! If you haven't seen, you can test new rules to see how much fraud they'd have prevented.
1 reply 0 retweets 0 likes -
Replying to @stripe
yes, but that involves a lot of trial and error. We are lazy. Personalized machine learning to the rescue?
1 reply 0 retweets 0 likes -
Replying to @windscribecom
1/ Definitely! That's where our automatic flagging of charges as high or medium-risk comes into play.
1 reply 0 retweets 0 likes -
Replying to @stripe @windscribecom
2/ By default, we’ll place charges into review if they are medium-risk using machine learning: https://stripe.com/radar/guide#machine-learning-basics …
1 reply 0 retweets 0 likes -
Replying to @stripe
Yes, I know, but is that generalized or the behavior/rules are tailored to each merchant? Fraud patterns could be different
2 replies 0 retweets 0 likes -
Replying to @windscribecom
2/ We can see what gets disputed for you and learn that some signals are more predictive for your business than for others.
1 reply 1 retweet 1 like
3/ You can aid this process by reviewing charges, giving refund reasons, etc. Feel free to email if we can help further!
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.