> Cornell researchers recently asked the question: Why do they still not let you vote down a song?

They do. "skip" does things other than skip the song.

They also had a dedicated dislike button and removed it years ago. Apparently what they are doing now works better.

> Specifically, they demonstrated that a listener is roughly 20 percent more likely to “like” a song if the algorithm is trained on 400,000 likes and dislikes, compared to an algorithm trained only on that amount of likes.

Building a naive recommendation engine and giving it more good data – paid for, and also not factoring in the difference in time spent acquiring it – will obviously yield better results in a direct comparison. Striking a comparison to what Spotify is doing is pretty naive.