|
|
Presentation: "Bayesian Inference with Foursquare Data"
Time:
Monday 10:50 - 11:50
Location:
Roebling/Gleason
Abstract:
Foursquare has an
enormous database of Users and Locations. However, when not much is known
about a specific user or a specific location, it becomes difficult to make
inferences. How can we leverage a large data set in order to make
educated guesses about the properties of specific data points which don't have
much information associated with it? The approach covers Bayesian logic,
Conjugate Priors, and belief propagation.
|
Max Sklar, Machine Learning Engineer, Foursquare
Max Sklar is an engineer and a machine
learning specialist. At Foursquare, his objective is to constantly make
the application smarter and more interesting for users. Among these
projects is improving Explore, which is Foursquare’s social recommendation
system.
His
passion for recommender systems have led him to study how to make inferences
with sparse information, and how to quantify uncertainty. This has lead
to an interest in Bayesian methods in order to put a little common sense and
intuition into data-based predictions.
Prior
to his position at Foursquare, Max contributed to the emerging location-based
social space with the creation of Stickymap, which was a website that
encouraged users to annotate a map with knowledge of their neighborhood.
As an Adjunct Instructor at NYU, Max enjoys sharing his views on
technology and computer science and sparking dialogue with the next
generation of engineers. As an undergraduate, he was also a talk radio host on Yale
Radio. Max holds an M.S. in Information Systems from NYU, and a B.S. in
Computer Science from Yale.
|
 |
| |
