This interactive data app examines how artist collaborations impact visibility, breakout potential, and sustained momentum on Spotify’s Top 200 chart. Developed as part of the Correlation One DS4A: Empowerment fellowship, the project was recognized with a Distinguished Fellow award and served as a launching pad for future instructional roles and mentorship.
Over the course of several months, I cleaned, modeled, and analyzed over 10,000+ tracks and 3 years of streaming data, building custom metrics to explore collaboration frequency, chart trajectory, and the network structure of contributing artists and labels.
The final product features more than 30 interactive visualizations implemented with Dash, Plotly, and Pandas, and deployed using Heroku. The tool enables users from record label executives to music industry researchers to filter by artist, genre, or label and evaluate how collaborations may accelerate track performance or enable cross-audience exposure.
- Designed 5 dashboard modules focused on track performance, label network structure, and collaboration metrics
- Built end-to-end ETL and visualization pipeline from Spotify’s Top 200 datasets
- Deployed publicly for live use via Heroku and featured as a model project in DS4A’s data science curriculum
GitHub Repository: JPSchloss/Spotify-Dash-Final