An AI-powered IPL analytics and match prediction platform built using Machine Learning, Streamlit, FastAPI, and real IPL match data.
This project combines cricket analytics, predictive modeling, live match simulation, and interactive dashboards to create a complete IPL intelligence system.
This project analyzes historical IPL data and predicts match outcomes using machine learning models.
It includes:
- 🤖 AI-based match win prediction
- 📊 Interactive IPL analytics dashboard
- 📈 Team and player performance analysis
- 🎯 Batting & bowling insights
- 💥 Boundary and six-hitting analysis
- 📡 Live match simulation
- 🔥 Player clustering using K-Means
- ⚡ FastAPI backend for predictions
- 🌐 Cricbuzz/CricAPI live match integration
- 1️⃣ Clone Repository:
- git clone https://github.com/your-username/IPL_COMMAND_CENTER.git
- 2️⃣ Install Dependencies:
- pip install -r requirements.txt
- 3️⃣ Run Streamlit Dashboard:
- streamlit run dashboard/app.py
- 4️⃣ Run FastAPI Server:
- uvicorn api_server:app --reload
- Python
- Pandas
- NumPy
- Scikit-learn
- XGBoost
- Plotly
- Streamlit
- FastAPI
- Requests
The dashboard includes:
- Interactive charts
- Radar visualizations
- Match comparison graphs
- Live score simulation
- Dynamic team analytics
Some future ideas for the project:
- Real live IPL API integration
- Deep learning models
- Player recommendation engine
- Fantasy team prediction
- Match commentary AI
- Deployment on AWS/Render/Streamlit Cloud
While building this project, I learned:
- Machine Learning workflows
- Feature engineering techniques
- API development using FastAPI
- Dashboard development with Streamlit
- Data visualization with Plotly
- Sports analytics concepts
- Real-world project structuring
- IPL Dataset Community
- CricAPI
- Streamlit
- Scikit-learn
- XGBoost
CntlShiftCode
If you liked this project, feel free to ⭐ the repository!