Music Discovery at Pandora
Finding the music of the moment can often be a challenging problem, even for humans with well-versed musical tastes. These challenges further explode into a myriad of complexities when attempting to construct algorithmic approaches for automatic playlist generation. A variety of factors play a role in influencing a listener’s perception of what music is appropriate on a given seed (e.g., musicological, social, geographical, generational), and these factors vary across different contexts and listeners. The talk will present an overview of recommendation at Pandora, followed by a deep dive into the challenges of recommending content in the long tail.
Erik Schmidt is a Senior Scientist at Pandora. Most recently, he led the development of Thumbprint Radio, a hyper-personalized product that has attracted over 20 million listeners to date. He has contributed numerous recommendation strategies to the Pandora ecosystem spanning playlists, station discovery, and concerts. Before joining Pandora, Schmidt was a postdoctoral researcher in the Music and Entertainment Technology Laboratory (MET-lab) at Drexel University in Philadelphia. His general research interests lie in the areas of machine learning, recommendation systems, and digital signal processing.