Smart Crop Recommendation and Yield Prediction System Using Machine Learning

Our project, Smart Crop Recommendation and Yield Prediction System Using Machine Learning, is developed to address the key limitations of traditional agricultural decision-making practices. Existing approaches primarily rely on farmer experience, regional advisories, and static guidelines that lack personalization, accuracy, and real-time adaptability. Farmers struggle to determine the most suitable crops for their specific soil and environmental conditions, leading to poor crop selection, resource wastage, and reduced productivity. To overcome these challenges, the proposed system leverages advanced Machine Learning algorithms — specifically Light Gradient Boosting Machine (LightGBM) and Random Forest — to analyze soil parameters (Nitrogen, Phosphorus, Potassium, and pH) and environmental factors (temperature, humidity, and rainfall), providing accurate and data-driven crop recommendations. The system performs multi-class classification on structured agricultural datasets and incorporates feature importance analysis to improve transparency. It is deployed through a Streamlit-based interactive web application, allowing users to input values and receive real-time crop recommendations instantly. The system provides a practical and accessible solution for farmers, agricultural researchers, and policymakers, enabling informed decision-making, optimized resource utilization, and promotion of sustainable farming practices.