Ethiopian Crop Yield Prediction using Machine Learning
Project Overview
This project applies Business Intelligence and Machine Learning techniques to analyze agricultural production data from Ethiopia and predict crop yield.
The project explores agricultural trends across regions and crop types and develops predictive models to support data-driven decision-making.
Dataset Features
- Year
- Region
- Crop Type
- Area Cultivated (Ha)
- Production (Kg)
- Yield (Kg/Ha)
Project Objectives
- Analyze agricultural production patterns
- Identify high-performing crops and regions
- Predict crop yield using machine learning
- Generate business insights for agricultural planning
Machine Learning Models
- Linear Regression
- Decision Tree Regressor
- Random Forest Regressor
Technologies Used
- Python
- Pandas
- NumPy
- Matplotlib
- Seaborn
- Scikit-learn
- Streamlit
Results
The Random Forest model achieved the best predictive performance and was selected as the final model.
Future Improvements
- Weather data integration
- Soil quality analysis
- Satellite imagery
- Real-time forecasting
Author
Mulugita Simegnew
Data Science Student