This module builds your first predictive models. You will start with correlation — measuring how two variables move together — and extend that intuition into linear regression with one predictor, then many. The second half asks the harder question: how do you know the model is any good? You will learn the standard regression error metrics, what each one rewards, and how to choose among them based on the business decision the model supports.
Learning Objectives
By the end of this module, you will:
- Explain what correlation measures and interpret its strength and direction
- Build and interpret simple and multiple linear regression models in Python
- Include categorical predictors and connect coefficients to business insight
- Recognize the limits of correlation and regression with respect to causality
- Explain how regression fits a line by minimizing the sum of squared errors
- Calculate and interpret R², MSE, RMSE, MAE, and MAPE
- Apply train/test splits and explain why generalization matters for deployment
