Abstract
This project introduces a machine learning-based system that predicts the most suitable crop for specific environmental and soil conditions. It leverages data on agricultural parameters, including nitrogen (N), phosphorus (P), potassium (K), temperature, humidity, pH, and rainfall. Using logistic regression, it classifies and predicts optimal crop types. Additionally, data analysis and K-Means clustering reveal patterns and group crops by similar environmental needs. Visualizations illustrate key agricultural factor distributions. The model, evaluated with a confusion matrix and classification report, offers practical applications for farmers, aiding in sustainable crop selection.