Accurate crop selection plays a pivotal role in enhancing agricultural productivity and ensuring sustainable farming practices. This research proposes a machine learning-based crop recommendation system that leverages soil parameters (e.g., pH, nitrogen (N), phosphorus (P), potassium (K)), climate variables (rainfall, temperature, humidity), and agronomic indicators to suggest optimal crops for specific agro ecological zones. Utilizing publicly available datasets and preprocessing techniques, a suite of classification models-including Random Forest, XGBoost, Decision Tree, K Nearest Neighbors, SVM, and Logistic Regression- is trained and evaluated in Python. Model performance is assessed through metrics such as accuracy, precision, recall, and F1 score. The ensemble-based models, particularly Random Forest and Gradient Boosting, exhibit superior performance. The proposed system supports decision making for farmers and extension services, enabling data-driven crop planning and contributing to resource optimization and food security
Crop Recommendation, Machine Learning, Soil Parameters, Weather Conditions, Random Forest, XGBoost, Python Implementation, Precision Agriculture, Classification Models, Sustainable Farming