Speaker "Jacob Burnim" Details Back



Fighting Online Fraud and Abuse with Large-Scale Machine-Learning and Deep Learning


Sift Science protects thousands of different businesses from all kinds of fraud and abuse, from a stolen credit card used to buy an airline ticket or a digital game, from a fake apartment or job listing, from a fraudulent money transfer, or from abuse of a referral program. In this talk, I'll discuss Sift's approach to building a machine learning system to detect all of these diverse kinds of fraud and abuse, including extracting features and training models on custom data specific to each business, handling imbalanced classes, effectively sharing learnings across our entire network to help each individual business, learning in real-time, accurately measuring our performance, and explaining our system's recommendations to users. I will also share how we have recently used deep learning to improved our accuracy. Attendees will learn techniques for predicting diverse kinds of online user behavior, especially infrequent bad (or good) behavior (feature extraction, modeling, evaluation, etc.), plus many lessons learned.


Jacob Burnim is a Principal Software Engineer at Sift Science, fighting online fraud and abuse with large-scale and real-time machine learning. He previously worked at Google on a machine learning system for ranking search results. Jacob has a Ph.D. in Computer Science from UC Berkeley and a B.S. in Computer Science and Mathematics from Caltech.