This text is certainly one of a two-part piece documenting my learnings from my Machine Learning Thesis at Spotify. You should definitely also try the second article on how I implemented Feature Importance on this research.
In 2021, I spent 8 months constructing a predictive model to measure user satisfaction as a part of my Thesis at Spotify.
My goal was to know what made users satisfied with their music experience. To accomplish that, I built a LightGBM classifier whose output was a binary response:
y = 1 → the user is seemingly satisfied
y = 0 → not a lot
Predicting human satisfaction is a challenge because humans are by definition unsatisfied. Even a machine isn’t so fit to decipher the mysteries of the human psyche. So naturally my model was as confused as one will be.
From Human Predictor to Fortune Teller
My accuracy rating was around 0.5, which is the worst possible consequence you’ll be able to get on a classifier. It means the algorithm has a 50% probability of predicting yes or no, and that’s as random as a human guess.
So I spent 2 months trying and mixing different techniques to enhance the prediction of my model. Ultimately, I used to be finally in a position to improve my ROC rating from 0.5 to 0.73, which was an enormous success!
On this post, I’ll share with you the techniques I used to significantly enhance the accuracy of my model. This text might come in useful at any time when you’re coping with models that just won’t cooperate.
As a consequence of the confidentiality of this research, I cannot share sensitive information, but I’ll do my absolute best for it to not sound confusing.
winter jazz music