Users Floating in Space: A Study in Recommendations


This talk covers several technical approaches that brought a music recommendation service into the AI era. In particular, this is a case study of a collaboration between machine learning experts (Unbox Research) and a music service company (Roon Labs). By implementing new personalization features, our joint work was able to significantly improve product quality and user engagement. This talk begins with the intuition behind the collaborative filtering (CF) method, which assigns a numeric representation to each user and product (this idea applies to basically any kind of content — not just music). The speaker will also touch upon several more advanced techniques that can augment a traditional CF personalization pipeline.

Tyler Neylon at SRK Headshot Day

Tyler Neylon
CEO, Unbox Research

Tyler has over a decade of experience developing machine learning systems for real-world applications. He built Google’s initial sentiment analysis engine in 2006. He also created robotics simulations for Open AI, developed natural language processing techniques for Primer AI, and co-founded the data science infrastructure company Zillabyte through Y Combinator. Tyler wrote the O’Reilly book Creating Solid APIs with Lua and has three patents focused on sentiment analysis. Tyler holds a Ph.D. in Applied Math, specializing in machine learning algorithms, from NYU.


Go to Top