Smart Crop Recommendation System

Developed a machine learning-based crop recommendation system that predicts the most suitable crop based on soil nutrients and environmental conditions.

The project uses a dataset containing Nitrogen (N), Phosphorus (P), Potassium (K), temperature, humidity, pH, and rainfall values. Multiple machine learning models were trained and evaluated, including Logistic Regression, Decision Tree, and Random Forest.

A web application was built using Streamlit, allowing users to enter soil and weather information and receive real-time crop recommendations.

Selecting the most accurate machine learning model, comparing model performance, handling multi-class classification, and deploying the trained model as an interactive web application.

Another challenge was understanding feature importance and interpreting model predictions to identify which environmental factors most influence crop recommendations.