Dear friends,

This summer we will have a series of sessions from leading engineering teams about their use of Storm and other real-time data processing frameworks. We will have great talks from: Spotify, Yodle and Twitter.

The Spotify team will start this series with following topic:

Spotifys Music Recommendations Lambda Architecture

At Spotify, one of the ways we surface personalized music recommendations to users is via the Discover page. The recommendations are powered by training large scale Matrix Factorization models on user listening history. Batch hadoop jobs run daily to build latent vectors for users, tracks, artists and albums.

However, this setup doesnt incorporate intra-day listening history. Furthermore, new users that log into Spotify and stream music will not receive recommendations until their second day using the application. To solve the problem, we leverage Storm and process user listens in real-time; this allows us to surface recommendations to new users as soon as they start listening to songs on Spotify. We shall discuss our framework, how we use Storm and challenges we faced building this system.

Speakers:

Emily Samuels (@emilymsa) is a Data Engineer at Spotify. She has worked on the Radio, Discover Page, and Playlist Recommendations. She graduated from the University of Michigan with a B.S. in Computer Science. She has worked in industry for seven years and was previously with FactSet Research Systems and Goldman Sachs. Her main interest is Big Data and she enjoys working with Hadoop, Storm, and NoSQL databases.

Esh V K (@eshvk) builds Machine Learning and Infrastructure products at Spotify.Previously he worked at StumbleUpon and Mozilla. Esh was in a PhD program in Machine Learning at the University of Texas, Austin.

Agenda:

6 :30 pm: Guest arrival & networking.

7: 00 pm: Spotifys Music Recommendations Lambda Architecture

8.00pm: Event ends.

If you missed our last meetup, "Completely real-time recommendations",materials are posted here:

http://events.mapr.com/NYCityStorm

Strata+Hadoop World in New York:

http://www.tqlkg.com/image-7592525-12229853-1433519484000

Save 20% on any pass with discount code UGNYCSUG20. Check out the impressive agenda and speaker lineup.

Strata conference is the most interesting Big Data event in New York. We negotiated20%discount for our group.

Strata + Hadoop World, happeningSeptember 29 - October 1is where
cutting-edge science and new business fundamentals intersect. Its a
deep-immersion event where data scientists, analysts, and executives
explore the latest in emerging techniques and technologies.