Saturday 21st April, 2012
11:00am to 11:30am
From The Hype Machine to Last.fm, music recommendation is now an everyday part of our lives. These services employ many techniques, from curated-playlists to content-similarity to collaborative filtering. But can music recommendation techniques tell us what we should be drinking before a concert? Or where to drink it? Or what tasty beverage best matches a meal? In this talk I’ll be briefly surveying music recommendation techniques, focusing on personalisation and content-based recommendation. I’ll then introduce a dataset of beer descriptions and ratings. We’ll apply the earlier techniques (some with slight modifications) to this rather more intoxicating domain, via a case study. When it’s all over, everyone should know the answer to that most important of questions: What beer will go best (for you) with this bacon?
(all code used in this talk will be available online under an OSS licence)
Thinking about beer, data, music; order varies over time. I do some of my best thinking on a bicycle. Fixing all the data @funandplausible. Sometimes academic.
Sign in to add slides, notes or videos to this session