This course provides a comprehensive, project-based introduction to applied machine learning using Python, with a focused emphasis on regression and classification techniques. You’ll begin with the foundational concepts of linear regression using Scikit-learn, learning how to prepare data, build models, and interpret output through real-world datasets like the Boston Housing dataset. From understanding bias-variance tradeoffs to visualising learning curves and prediction errors, you'll gain a solid grasp of regression analysis.

The course then dives into classification with logistic regression, introducing key concepts like the sigmoid function, decision boundaries, and evaluation metrics such as precision, recall, and the AUC-ROC curve. With the Titanic dataset, you'll conduct exploratory data analysis, handle missing values, apply one-hot encoding, and use recursive feature elimination for improved accuracy.

Support Vector Machines (SVM) are then explored in depth, including kernel functions and the role of feature scaling. You’ll build linear and kernel-based SVM models using the Breast Cancer dataset, gaining insights into how SVMs handle complex classification tasks.

Finally, the course covers cross-validation and hyperparameter tuning techniques, including K-Fold CV, Grid Search, and Randomised Search. You’ll learn how to avoid overfitting and improve model generalisation by applying regularisation techniques and fine-tuning hyperparameters for better performance.