Machine Learning at Sift Science

Main Speaker: Doug Beeferman (Sift Science)

Title: Feature Engineering for Real-Time Fraud Detection

Abstract: This talk will explore some of the joys and pitfalls of applying machine learning to Internet activity. It'll focus on the process that Sift Science uses to develop features for its realtime fraud detection service, covering some of the specific evaluation and modeling problems that are unique to this kind of data.

Bio: Doug Beeferman is a software engineer at Sift Science, formerly at Google and Lycos. His focus throughout his career has been applications that analyze logs of user activity such as search and web logs. He is also interested in text and speech processing.

Lightning Talk Speaker: Andrey Gusev (Sift Science)

Title: Machine Learning Infrastructure

Abstract: Sift Science uses online and large-scale machine learning to detect fraud for hundreds of web sites in realtime. In this talk I'll describe how we leverage HBase and Hadoop to power our learning infrastructure including: how we train and build our models, store and update model parameters, and provide real-time predictions that update online.

Bio: Andrey is ML infrastructure tech lead at Sift Science and enjoys machine learning, search, NLP, and distributed systems. Before Sift, Andrey was a lead engineer at salesforce.com (http://salesforce.com/) working on search and machine learning systems; Andrey holds CS degrees from Stanford University and University of Illinois.

Tentative Schedule:
6:30pm-7:00pm - socializing

7:00pm-7:15pm - lightning talk (Andrey Gusev)

7:15pm-8:15pm - main presentation (Doug Beeferman)

8:15pm-9:00pm - socializing

Important Notes:

• PLEASE REMEMBER TO SPECIFY YOUR FULL FIRST AND LAST NAME WHEN REGISTERING! Building Security requires this.

• Photo ID will be required.

• Due to the nature of the content, this event will NOT be recorded.