This analysis presents a robust framework for crop yield prediction using machine learning. The process starts with an exploratory phase, leveraging bar charts, line graphs, and histograms to examine the relationships and distributions of key factors like crop yield, rainfall, pesticide use, and temperature. These visualizations uncover patterns in the data, offering foundational insights to guide model building. The data is then preprocessed, which includes encoding categorical variables and splitting the dataset into training and testing sets. Using the cleaned data, two popular machine learning regression models, XGBoost and Random Forest, are applied to predict crop yield. Performance metrics such as root mean squared error (RMSE) and accuracy gage each model’s effectiveness, with XGBoost achieving 96% accuracy and Random Forest slightly surpassing it at 97%. Additionally, scatter plots map the models’ predicted values against actual outcomes, offering a clear visual representation of their predictive accuracy. This visual feedback not only clarifies the strengths of each model but also showcases their ability to capture trends in the data. This notebook serves as a comprehensive resource, combining exploratory analysis with advanced machine learning techniques to yield actionable insights and optimize prediction accuracy for crop yield.