CROP RECOMMENDATION USING XGBOOST ALGORITHM

Precision agriculture, a modern farming approach leveraging soil characteristics, weather data, and crop yield information, minimizes crop failures and aids farmers in strategic decision-making for optimal yields and profits. To address the agrarian crisis, this project focuses on enhancing recommendation systems for informed crop cultivation decisions. Using an augmented dataset from various Indian sources, including soil and weather information, the study employs the XGBoost algorithm to predict the most suitable crops. Unlike the baseline Random Forest model with 87% accuracy, our proposed XGBoost model achieves an impressive 99.32% accuracy, showcasing its superior performance. This project underscores the transformative impact of advanced machine learning techniques in revolutionizing crop recommendation accuracy for farmers, ultimately contributing to sustainable and profitable agriculture.