Designing Machine Learning Algorithms for Hadoop

This event we will have 2 speakers Erik from Spotify and Blake from Foursquare

We will be livestreaming this event. URL: http://www.livestream.com/spotifyevents (The password prompt will be disabled 10-15 minutes before the event begins.)

Description and Bios:

Blake Shaw - Foursquare
Every day millions of Foursquare users contribute to a rich stream of location data as they move around cities carrying their mobile devices. This data allows us to better understand how people interact with places all over the world. In this talk, we'll walkthrough the various large-scale data mining and machine learning algorithms we have implemented using Hadoop, and how these algorithms power our recommendation engine as well as our venue search API.

Blake Shaw is currently a Data Scientist at Foursquare, a location-based service that helps people keep up with friends and discover new places. At this NYC startup, Shaw applies machine learning algorithms to large spatiotemporal datasets in order to better understand patterns of human mobility. Shaw holds a Ph.D. in Computer Science from Columbia University, and his research has appeared at a variety of conferences including NIPS, ICML, WSDM, and AISTAT. Shaw was also the lead developer of CabSense, a mobile app for predicting the best street corners in New York City for catching taxicabs.

Erik Bernhardsson - Spotify
Spotify uses collaborative filtering to power features like radio, related artists, and the "discover" page. These recommendations are typically based on various latent factor models, like PLSA and other similar models. We will talk about how to scale up the algorithms to run in Hadoop on large data sets, typically 100s of billions of data points, and how to use the output to come up with music recommendations.
Erik Bernhardsson is an Engineering Manager at Spotify, focusing on music discovery and machine learning. He has a master's degree in Physics from KTH in Stockholm.

Special thanks for Spotify sponsoring this event!!