Music Recommendation System
- 0 Collaborators
My project revolves around the idea of how people search for music which they would like to listen to at the moment according to their mood, the song's popularity or any factor which impacts the user and satisfies them. This project serves to satiate that need for users and recommends them songs. ...learn more
Project status: Published/In Market
Intel Technologies
Intel CPU,
Intel Python
Overview / Usage
This project recommends songs to the user using the million songs data set. The following problems are being solved through it:
-
They handle the duty of choosing what to listen to for the listener.
-
When they listen to some genre, they don’t feel familiar with – recommendations are a way to go about it.
-
On the other hand, experienced listeners might use such feature to learn about similar artists to those they already like or explore unknown lands in the genre they love.
-
Since music dataset is too big, we need a recommender to recommender as per our mood , as per your taste.
Methodology / Approach
This project solves the recommendation problems using two models:
- Popularity Based Model
- Sort songs by popularity in a decreasing order
- For each user, recommend the songs in order of popularity, except those already in the user’s profile
- Collaborative filtering
- Item based : songs that are often listened by the same user tend to be similar and are more likely to be listened together in future by some other user.
- User based : users who listen to the same songs in the past tend to have similar interests and will probably listen to the same songs in future.
Technologies Used
Various tools were used such as :
-
Visual Studio Code(Code editor)
-
Python
-
Pandas module
-
Numpy module