Machine Learning

Overview

The complete supervised and unsupervised learning toolkit with scikit-learn. You learn how algorithms work, how to evaluate them honestly and how to tune them for real data.

What you will be able to do

• Frame business problems as ML tasks
• Train regression, classification and clustering models
• Engineer features and handle imbalanced or missing data
• Evaluate with the right metrics and avoid leakage
• Tune and explain models and ship them in a simple app

1. The ML workflow and data splits
2. Linear and logistic regression
3. Decision trees, random forests and gradient boosting
4. k-NN, SVMs and Naive Bayes
5. Clustering and dimensionality reduction
6. Feature engineering and pipelines
7. Model evaluation, validation and tuning
8. Explainability (SHAP) and fairness
9. Deploying a model with Streamlit

Tools you will use

Choose your class time

Every class covers the same lessons with the same tutors. Take it on campus, live online with recordings, or mix both week by week at no extra cost.

Weekend classes have fewer hours each week, so they run longer to cover the same course. Public holidays are made up on the following Friday. Next intake starts 3 November 2026. See all class times and intakes.

Fees and payment

Questions about this course

See all questions arrow_forward