An interactive Streamlit dashboard analyzing 1M+ YouTube records to identify engagement trends, content performance patterns, and recommendation insights.
Analyze views, likes, comments, and engagement to identify patterns that influence content performance and help content creators make data-driven decisions.
- 📈 Engagement trend analysis — views, likes & comments over time
- 📺 Channel and category insights — performance breakdown by content type
- 🎛️ Interactive filters and metrics dashboard
- 🔍 EDA — identifying key factors that drive audience engagement
- 💡 KPI tracking — content performance indicators at a glance
| Tool | Purpose |
|---|---|
| Python | Core programming language |
| Pandas & NumPy | Data manipulation & analysis |
| Streamlit | Interactive dashboard UI |
| Power BI | Additional visual reporting |
| Kaggle | Dataset source (1M+ records) |
youtube-analytics-dashboard/
│
├── youtube_recommendation.py # Main Streamlit app
├── requirements.txt # Dependencies
└── README.md # Project documentation
- Clone the repository
git clone https://github.com/Shiva-keerth/youtube-analytics-dashboard.git
cd youtube-analytics-dashboard- Install dependencies
pip install -r requirements.txt-
Download the dataset from Kaggle and place it in the project folder
-
Run the Streamlit app
streamlit run youtube_recommendation.py- Analyzed 1M+ YouTube records to uncover content performance patterns
- Identified content factors that improved audience engagement by ~30%
- Built interactive KPI dashboard to support data-driven content decisions
⚠️ Dataset not included — download from Kaggle
Shiva Keerth G
📧 gantishivakeerth@gmail.com
🔗 GitHub | LinkedIn