27.May.2011 at 15:50 by Anonymous
Easily the best presentation of the conference. Clear, thorough, and useful; good pacing and diagrams. Absolutely excellent.
Teaching Your Machine to Find Fraudsters
Ian Barber (27.May.2011 at 10:00)
Talk at php|tek 11 (English - US)
When dealing with money online, fraud is an ongoing problem for both
consumers and sellers. Researchers have been developing statistical
and machine learning techniques to detect shady sellers on auction
sites, spot fraudulent payments on e-commerce systems and catch click
fraud on adverts. While there is no silver bullet, you will learn to
flag suspicious activity and help protect your site from scammers
using PHP and a little help from some other technologies.
Quicklink: https://joind.in/3429
Who are you?
By clicking this button you are declaring that you are the speaker responsible for it and a claim request will be sent to the administrator of the event.
If the claim is approved you will be able to edit the information for this talk.
Are you sure?
Comments
27.May.2011 at 15:56 by John Kary
This is a very rich talk with a lot of potential.
Give a definition of Fraud up front, and the different types of fraud you're attempting to mitigate during your talk. Right now this is in the middle of your talk. Move all the fraud types to the front, then the progress through that list and show how to mitigate each one. This will give the audience a roadmap for what you're going to talk about, and if they're not familiar with the problem domain, it can help bring them in.
The click fraud stuff is awesome, and you could probably do a talk on that alone, but it's very dense with code and math. The code itself is hard to follow as you're talking about it. Some of this was due to code formatting and variable naming, but I understand you're trying to condense it to fit on the slide. This might be better abstracted across several slides as simple math equations, instead of code, and displayed in the same order as your code uses.
Some of my feedback may be due to my own unfamiliarity with the problem domain, so keep that in mind too :)
Great delivery!
27.May.2011 at 16:29 by Jason E. Sweat
Great talk, again clearly knowledgeable on the subject, good pacing and good delivery. I will definitely investigate the svm extension for my next classification need. Thank you.
27.May.2011 at 16:40 by Todd Wanchic
Absolutely solid talk on detecting fraud. I liked that you went over some red flags for fraud that many people over look.
27.May.2011 at 15:48 by Rafael Dohms
Very interesting talk on a topic not usually covered, i really enjoyed the linearity in teaching the different solutions, so going from the simplest and showing the downfalls and advantages and then progressing to other solutions, very well delivered.