Predictive Modeling with Python

This intermediate course path introduces predictive modeling with Python through hands-on work with regression and the California Housing Dataset. It is designed for learners who have some programming and data experience and want to build models that support data-driven prediction. You will start with the foundations of predictive modeling, then learn how to prepare data by handling missing values, outliers, and categorical variables. From there, you will build regression models including polynomial, lasso, and ridge regression. The path also covers advanced algorithms available in Scikit-Learn, such as support vector machines, decision trees, random forests, and neural networks. You will practice evaluating model performance and applying optimization techniques to improve accuracy and robustness.

Syllabus

Prepare datasets for predictive modeling by handling missing values, outliers, and categorical variables
Build regression models in Python, including polynomial, lasso, and ridge regression
Train advanced machine learning models such as support vector machines, decision trees, random forests, and neural networks
Evaluate predictive model performance using appropriate regression metrics
Improve model accuracy and robustness through evaluation and optimization techniques
Apply predictive modeling workflows to housing data using Python and Scikit-Learn