Towards Recommender System Optimization: Our Data Tool for Algorithmic Optimization on Spotify [Part 1]

most existing recommender systems do not have access to any data outside of their own supply-side platform. For example, if Lee watches lots of true-crime documentaries on Netflix, then it stands to reason that he might also enjoy listening to true-crime podcasts on Spotify and buying true-crime books on Amazon. But because each of those platforms ... See more

The effectiveness of this approach varies widely. Why does a playlist generated off a single song on Spotify work so well and yet its podcast recommendations feel generic? Why, after spending years and millions of dollars on research, including the fabled Netflix prize, do Netflix's recommendations still feel generic, and why doesn't it really matt... See more

To start I like to describe where music consumption is now. It's quite obvious to avid music consumers that you can create a better playlist yourself than could an algorithm. If you really wanted to sit down to create that perfect playlist for your day, you'd probably be able to do a pretty good job by yourself doing it. Spotify will do an okay job... See more

A recommender system is a digital product that uses AI to generate personalized recommendations. Over the past 20 years, recommender systems have come to play a central role on many large online platforms. Some recommender systems run prominently in the foreground of the user experience (UX), and operate as core features or even brands (such as Spo... See more

He did not mention as he was not able to witness the power of the algorithms in the music business, thanks to these platforms being able to gather organize and analyze data to the point of being able to learn what sounds and lyrics were desired by who, in what locations and when.