Welcome to COMS 4771 Spring 2021 large-scale regression task. Your goal for this assignment is to develop a good quality regressor for the given dataset.

The given dataset comes from musical songs domain. It consists of about 1/2 Million songs from 20th and 21st century. The task is to predict the year the song was released given the musical content of the song.

To ease the preprocessing burden, each song (observation) has already been vectorized into 90 high quality timbre based features.

You can use any resource/code/package/toolbox that is publicly available to develop your regressor. Your primary goal for this assignment is to develop a good quality song-year predictor. (This of course will be only possible if you employ good Machine Learning practices).