Discovering Things We Truly Love

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

Recommendations kills Favorites: AI-driven recommendations transcend our historical go-to’s. Rather than compulsively saving playlists that i discover and love on Spotify, I’ve surrendered myself to the algorithms. It was really the radio feature plus the new “enhance” feature that did it. I now trust that any song I like leads to a playlist I will... See more

This problem is almost impossible to fix in a culture that relies heavily on algorithms. The algorithm is, by definition, a repeating pattern that always looks backward. It does something in the future based on what worked in the past.

So the algorithm that recommends music or videos on a web platform will never deliver a totally fresh and new expe... See more

In a way, recommender systems have become some of the most important opinion leaders in the industry. The same way a recommendation from a trusted friend can go a long way — compared to, let's say, an ad you see on Instagram — a recommendation from a "trusted" algorithm brings about a sort of post-social proof.