Dance Hit Prediction in Journal of New Music Research
I'm happy to announce that the latest issue of Journal of New Music Research (special issue on Music and Machine Learning) features a publication about Dance Hit Prediction
Record companies invest billions of dollars in new talent around the globe each year. Gaining insight into what actually makes a hit song would provide tremendous benefits for the music industry. In this research we tackle this question by focussing on the dance hit song classification problem. A database of dance hit songs from 1985 until 2013 is built, including basic musical features, as well as more advanced features that capture a temporal aspect. A number of different classifiers are used to build and test dance hit prediction models. The resulting best model has a good performance when predicting whether a song is a ‘top 10’ dance hit versus a lower listed position.
Try out the model for yourself on dance hit prediction website.