The idea is to build a music recommendation system. Building a music recommendation system is a common task that is faced by Spotify, iTunes, JioSaavn, Pandora, etc . The underlying goal of the music recommendation system is to personalize content and identify relevant data for our audiences. The parameters to identify contents can be genre, artist, album, label, etc.
There are 3 types of recommendation system: content-based, collaborative and popularity-based.
Real world data is used to train the model.The dataset contains millions of training examples to train on. The dataset contains two files: triplet_file and metadat_file. The triplet_file contains user_id, song_id and listening_time. The metadat_file contains song_id, title, release_by and artist_name.
triplets_file = 'https://static.turi.com/datasets/millionsong/10000.txt'
songs_metadata_file = 'https://static.turi.com/datasets/millionsong/song_data.csv'
Please refer to Project_Report.pdf for detailed report about the project.
This project was done as a part of Computational Intelligence Course in B.Tech CSE. other contributor: https://github.com/vkumar7796
source code: Song_Recommender_Python.ipynb