Re:Blood, Sweat and Years: Raising Money as a Deep Learning ...
by vonnik on Tuesday October 25, 2016 @04:49PM
(#12791541)
Hi there! A lot of the fraud detection we do is actually anomaly detection, where we're not training a classifier on a labeled dataset, but instead creating a model that can surface unusual behavior. The subset of data that we surface is then passed to human analysts. What they care about, generally, is a low false positive rate, because false positives waste their time. We talk about this a bit more here: https://skymind.io/case-studies/orange Sorry if that doesn't quite answer your question.
[ Parent
| on HN ]
Re:Blood, Sweat and Years: Raising Money as a Deep Learning ...
by yingxie3 on Tuesday October 25, 2016 @08:18PM
(#12792943)
For fraud detection such as what you did for orange, is there a rule of thumb on how much data one would need? Before heading down the path I would like to know whether my problem is solvable given the amount of data I have. Thanks in advance!
Re:Blood, Sweat and Years: Raising Money as a Deep Learning ...
by agibsonccc on Tuesday October 25, 2016 @08:19PM
(#12792946)
We were in the terabytes. A viable proof of concept could be built with a few gigs of transactions to validate the idea though.
The main bit with orange that isn't in the marketing material: We used unsupervised methods for this, not supervised.