The sustainability and profitability of modern agriculture hinge critically on selecting the optimal crop for specific geographical and environmental conditions. Traditional crop selection methods often rely on generalized historical data or farmer intuition, failing to account for the maximum achievable yield potential. This limitation frequently leads to suboptimal land use and reduced profitability. he optimization of agricultural output requires selecting not just a suitable crop, but the highest-yielding crop for specific environmental conditions. Traditional methods of crop selection often lack the scientific depth to accurately forecast crop productivity, leading to suboptimal yields and resource mismanagement. This research proposes a Yield-Aware Crop Selection System Leveraging Machine Learning (ML) to address this gap. The system utilizes a robust classification model to perform the initial recommendation based on key soil parameters (N, P, K, pH) and climatic factors (temperature, humidity, rainfall). Comparative evaluation showed that the Random Forest algorithm delivered the highest accuracy for crop suitability, achieving 98.8%. This system is architecturally designed to integrate a subsequent yield prediction model (using regression analysis) to provide the expected output, thus enabling farmers to make a final, yield-optimized decision. The highly accurate selection phase lays a reliable foundation for maximizing profitability, promoting sustainable farming, and modernizing agricultural practices through data-driven insights. By integrating robust classification with precise yield regression, this system transforms crop selection from a suitability problem into an optimization problem. This approach offers farmers an effective tool for boosting agricultural output, improving resource efficiency, and enhancing economic viability.