This chapter introduces regression-based supervised machine learning methods, emphasizing their application with built-in datasets in R. Readers are guided through core techniques including linear regression, polynomial regression, logistic regression, ridge regression, and lasso regression, each applied to predicting different types of outcomes. Practical instruction covers model fitting, interpretation of coefficients, and evaluation using common metrics such as R-squared, Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). To support learning, ChatGPT is incorporated as a coding assistant, helping generate R scripts, troubleshoot programming errors, and clarify complex statistical or machine learning concepts. This interactive approach reduces barriers to understanding and encourages experimentation. By working directly with accessible datasets, learners gain valuable hands-on experience that builds technical proficiency while reinforcing critical evaluation skills. The chapter also stresses responsible use of regression methods in public health, connecting technical training to meaningful research and practice.