Back
Year
2024
Tech Stack
Python, pandas, NumPy, Matplotlib, Seaborn, scikit-learn
Description
An automated data analysis pipeline built to explore Spotify track metadata
and audio features to understand patterns behind popularity and genres.
Why this project matters
This project focuses on turning large, messy datasets into structured insights. It highlights the importance of reproducibility and clear analytical workflows when exploring consumer behaviour data.
Key Features
Technical Highlights
Why this project matters
This project focuses on turning large, messy datasets into structured insights. It highlights the importance of reproducibility and clear analytical workflows when exploring consumer behaviour data.
Key Features
- 🎵 Audio feature analysis
- 📊 Trend exploration
- 🤖 Popularity prediction models
- 💾 Automated reporting
Technical Highlights
- 🧠 Modular pipeline design
- 📈 Visual exploratory analysis
- 🤖 ML models with scikit-learn
- 🛡️ Data validation
My Role
- 📦 Designed data pipelines
- 📊 Conducted exploratory analysis
- 🤖 Implemented ML models
- 📈 Built visual outputs