A Machine Learning-Based Precision Agriculture System for Crop Recommendation and Yield Prediction

Abstract: Agriculture plays a vital role in the economic and social development of India, yet many farmers continue to rely on traditional decision-making practices for crop selection and production planning. Such conventional methods often lead to inappropriate crop choices, inefficient resource utilization, and inconsistent yield outcomes. To address these challenges, this paper presents a machine learning-based precision agriculture system for crop recommendation and yield prediction. The proposed system utilizes a Random Forest Classifier to recommend the most suitable crop based on critical soil and environmental parameters such as nitrogen, phosphorus, potassium, temperature, humidity, pH, and rainfall. In addition, an ensemble regression framework combining Random Forest and XGBoost is employed to predict crop yield using historical agricultural and climatic data from different Indian states. The system also integrates real-time weather support and expert consultation features to improve decision-making for farmers. Experimental results demonstrate a crop recommendation accuracy of 96.3% and an R² score of 0.887 for yield prediction, indicating high reliability and practical applicability. The proposed framework provides an intelligent, scalable, and farmer-centric solution for smart agriculture and precision farming applications, with significant potential to improve agricultural productivity and support data-driven farming decisions.