Project 4 | Spotify Listening History Analysis 🎧📊

Exploratory data analysis is one of the most powerful ways to understand human behavior through real-world data. In this project, I analyzed Spotify streaming history from two users to uncover patterns in engagement, repetition, discovery habits, and listening style.

This dashboard demonstrates my ability to clean raw time-series data, engineer behavioral metrics, and communicate insights through interactive visualization. In real-world applications, this type of analysis supports personalized recommendation systems, audience segmentation, and product engagement strategy for streaming platforms.

Links 🔗

View Dashboard Report 📊 GitHub Folder 💻

Project Overview 📄

This project transforms raw Spotify listening logs into a behavioral engagement dashboard. By comparing two users across volume, temporal habits, artist diversity, and skip/shuffle behavior, the analysis highlights differences between habitual listening and exploratory discovery.

Project Workflow 🪜

P4 - S1 Data Wrangling: Cleaning timestamps, merging histories, feature engineering
P4 - S2 Behavioral Metrics: Engagement, repetition, discovery, skip/shuffle rates
P4 - S3 Visualization: Plotly figure development + dashboard structuring
P4 - S4 Reporting: Exporting a static interactive HTML dashboard for deployment

Dashboard Deliverable 📷

Main Output: Interactive Spotify Listening Dashboard

Includes 11 figures covering engagement volume, temporal consistency, artist repetition, album diversity, and skip/shuffle behavior patterns.

Open Full Dashboard

Key Results 🟰

Engagement: User A demonstrates more consistent listening volume over time.
Diversity: User B explores a broader range of artists and albums monthly.
Listening Style: Skip and shuffle behavior reveal distinct consumption preferences.
Behavioral Shifts: Discovery trends alternate yearly, with User B peaking in the final year.

Technical Stack 🔨

Core: pandas, NumPy

Visualization: Plotly Express, Plotly Graph Objects

Dashboard Export: Static interactive HTML reporting

Environment: Jupyter Notebook + GitHub Pages deployment

Ethical Considerations ⚖️

Listening data anonymized (no personal identifiers)
Behavioral analytics used only for insight, not surveillance
Dashboards designed for transparency and interpretability
Recommendation use would require consent and opt-out controls