Customers Who Bought Music Also Bought Beer
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)
Ben is obsessed with data, beer, and music, not necessarily in that order. He has a PhD from the Intelligent Sound and Music Systems group in the Computing Department at Goldsmith University of London. His work there focused on merging social and acoustic similarity spaces to drive playlist creation and related user-facing systems. He is an expert on metadata, structured data, the semantic web and recommendation systems. In his spare time, he is a co-chair of the annual international Workshop On Music Recommendation And Discovery, has given an Ignite London talk about beer styles, occasionally DJs, is an accredited beer judge and homebrews beer. He thinks bios in the third person are weird but figures that’s how they’re meant to be written.