This project focused on building a complete data analytics pipeline to monitor and evaluate YouTube channel performance metrics using the YouTube Data API v3, Python, and SQL. I engineered a system to automatically extract video-level statistics such as views, impressions, likes, and comment counts, storing daily data snapshots in a structured SQL database for time-series analysis. This automation eliminated manual tracking and enabled consistent, scalable data collection across multiple video categories and upload periods.
Once the data pipeline was established, I conducted comprehensive exploratory and statistical analysis in Python to uncover patterns in audience engagement, retention, and growth. Techniques such as correlation and regression modeling helped quantify relationships between variables like content type, video length, and upload frequency, revealing the factors most strongly associated with audience reach and performance consistency. These findings provided meaningful insights into how production and scheduling decisions could impact viewership and subscriber dynamics.
To enhance interpretability, I designed an interactive Power BI dashboard that visualized audience growth, engagement ratios, traffic sources, and category-level performance. Using DAX calculations and dynamic filters, the dashboard allowed real-time exploration of trends while simplifying complex metrics into intuitive visuals. This analytical interface offered a clear understanding of content strategy effectiveness, enabling data-driven recommendations to improve engagement and visibility.
By combining API integration, statistical modeling, and visualization, the project demonstrated the value of automation and structured analytics in understanding digital content ecosystems. It bridged raw platform data with actionable insights, providing a scalable framework for ongoing content performance evaluation and strategy optimization.
