Building a Large Music Recommender Leveraging AI, Deep Learning and Human Expertise | Òscar Celma

Pandora began with The Music Genome Project, the most sophisticated taxonomy of musicological data ever collected and an extremely effective content-based approach to music recommendation. But what happens when you have a decade of additional data points, given off by more than 70 million monthly users who have created 12+ billion personalized radio stations and given 90+ billion thumbs? This session will look at how the interdisciplinary team at Pandora goes about making sense of these massive data sets to successfully make large-scale personalized music recommendations to the masses. Following this session the audience will have an in-depth understanding of how Pandora uses Machine Learning (ML) to determine the perfect balance of familiarity, discovery and relevance for each individual listener, measures and evaluates user satisfaction, and how our online and offline ML architecture stack plays a critical role in playing the right song, at the right time, for the right listener. Visit the largest developer playground in Europe! https://www.wearedevelopers.com/ Facebook:   / wearedevelopers   Twitter:   / wearedevs   Instagram:   / _wearedevelopers   #WeAreDevs