Data architecture for a world of music, Lars "Lalle" Albertsson, Spotify

Abstract

The millions of people that use Spotify each day generate a lot of data, roughly a few terabytes per day.  What does it take to handle datasets of that scale, and what can be done with it?  I will briefly cover how Spotify uses data to provide a better music listening experience, and to strengthen their busineess.  Most of the talk will be spent on our data processing architecture, and how we leverage state of the art data processing and storage tools, such as Hadoop, Cassandra, Kafka, Storm, Hive, and Crunch.

Last, I'll present observations and thoughts on innovation in the data processing aka Big Data field, which hopefully will lead to a fruitful discussion for those that are interested.

Bio

Lars "Lalle" Albertsson spent his early career at SICS, researching network protocol implementation, operating
systems, and test & debug tools for multithreaded applications.  In his industrial life, he has been building server machines at Sun Microsystems, worked on Google chat & hangouts, created natural language processing systems at Recorded Future, and built low-latency stock exchange systems at Cinnober.  He is now an engineer at Spotify's data processing team, which builds the core dataset processing pipelines and also provide a Big Data toolchain for data-centric feature development.

Free of charge. Please register here.

Date/time: 
Wednesday, March 12, 2014, 14:00
Location: 
SICS, Knuth seminar room
Electrum building, Isafjordsgatan 22
Kista
Sweden
SE
Contact: 
Sverker Janson