Our project is centered around a clustering algorithm for songs belonging to a users playlists, wether it be 1 or 10. We will then output the recommended playlists per our clustering algorithm. We are currently thinking of implementing a K-Means clustering algorithm that allows the user to choose the number of playlists they want.
The challenges we anticipate in developing a properly functioning model are:
- User authorization to interact with the Spotify Web API
- Data extraction, both in gathering the data and choosing what data to use, hence point 3.
- Feature extraction and engineering
- Connecting a React-based frontend to a Flask API
The skills we will need to learn are:
- Exploratory Data Analysis using Pandas, Seaborn, and Matplotlib
- Feature Extraction to improve accuracy and reduce training time
- Model building
- Key Performance Indicators to measure our progress
- Full stack web development
+-- backend -> Flask API server
| |
| +-- server.py -> server entrypoint
|
+-- frontend -> React frontend
|
+-- EDA -> initial EDA file
|
+-- Sptofy Clustering -> clustering testing/tuning
Niccolo Nobili
- Pitt CS, 2025
- [email protected]
- Check out my Personal website or LinkedIn
Amaan Kazi
- Pitt Bioengineering, 2022
- [email protected]
- Check out my LinkedIn
Pranay Jain
- Pitt Bioengineering, 2022
- [email protected]
- Check out my Personal website or LinkedIn
Adam Powley
- Pitt Computational Biology, 2024
- [email protected]