Predicting crop yields with high accuracy is essential for precision agriculture, especially in countries like India where variable climate and diverse soil conditions strongly influence productivity. In this chapter, we develop a machine learning framework to forecast crop yield using a dataset that integrates soil characteristics, nutrient levels (N, P, and K), weather variables such as temperature, humidity, and wind speed, along with the categorical details of crop and soil types. Three ensemble-based models, Random Forest, Gradient Boosting, and CatBoost, were trained and assessed using regression metrics including RMSE, MAE, MSE, and R2. Among these, Random Forest achieved the best performance (R2 = 0.9746), followed by CatBoost (R2 = 0.9704), while Gradient Boosting showed lower accuracy (R2 = 0.8988). Analysis of feature importance highlighted temperature, humidity, and soil quality as the most influential factors affecting yield. These findings demonstrate the effectiveness of ensemble learning methods for reliable and efficient agricultural forecasting. The study also points to their potential integration into decision-support systems for farmers. Finally, the chapter discusses practical implications for agri-technology adoption and policy and suggests future directions, including the use of temporal models and hybrid AI–physical approaches.