Introduction to Machine Learning

Supervised and unsupervised learning end to end — train, tune, evaluate and explain models with scikit-learn.

⏰ 8 weeks🎯 Standard🧩 Certificate🖥 Any device · our GPUs

Generated from this course

🎯 About this course

This course teaches the workflow of machine learning, not just the algorithms. You will frame problems, build leak-free scikit-learn pipelines, compare linear models and tree ensembles, explore data with clustering and PCA, choose metrics and thresholds that match a real decision, and learn to spot leakage, unequal performance and misleading explanations.

Every topic ends in an auto-graded lab, and the applied studio has you predict customer churn end to end and write a one-page model card.

Who it is for

Learners who know some Python and want to become genuinely competent at supervised and unsupervised learning.

What makes it different

The emphasis is on not fooling yourself — validation, baselines, leakage and fairness are taught as core skills, not footnotes.

By the end you will be able to

Frame a business problem as a supervised or unsupervised ML task and select an appropriate baseline and metric.
Build leak-free scikit-learn pipelines that handle missing values, categorical features and unseen categories.
Train and tune linear models and tree ensembles, and diagnose underfitting and overfitting.
Apply clustering and dimensionality reduction to explore unlabelled data and choose parameters without labels.
Evaluate models with metrics and thresholds that match a real decision, using cross-validation with uncertainty.
Detect data leakage, measure performance across groups and explain model behaviour to stakeholders.
Deliver an end-to-end predictive workflow with a model card documenting purpose, metrics and limitations.

Curriculum

Topics covered

Core topics 6 topics

The end-to-end ML workflow
The end-to-end ML workflow: frame the problem, split the data, build a pipeline, evaluate, iterate.
Regression and classification
Linear and logistic models, regularisation, and how to tell under- from overfitting.
Trees, random forests and gradient boosting
Decision trees, random forests and gradient boosting — the workhorses of tabular ML.
Clustering and dimensionality reduction
Unsupervised learning: find structure without labels using clustering and dimensionality reduction.
Model evaluation, validation and metrics
Choose metrics that match the decision: precision, recall, ROC/PR curves, thresholds, and honest validation.
Data leakage, bias and explainability
Data leakage, fairness across groups and explaining models — the three ways a good metric hides a bad model.

Course at a glance

See how this course is built

Where the time goes

Longer spokes mean more hours on that module.

Course roadmap click a step

Try a lesson0 / 3

Sample questions from this course. Your progress is kept only in your browser.

Week by week

Drag the slider, or press play, to walk through the course and see what you will have built by each week.

Week 1 of 8

Wk 1–3

Supervised learning

You produceA tuned classifier with a proper train / validation / test setup

Wk 4–5

Ensembles and unsupervised methods

You produceA clustering or segmentation analysis on real data

Wk 6–8

Evaluation, explainability and project

You produceA documented model with an evaluation report — the certificate project

What you'll build

A validated scikit-learn pipeline

A leak-proof pipeline with a baseline and stratified cross-validation on a real-style dataset.

Metrics and threshold analysis

A report justifying the chosen metric and decision threshold from a stated business constraint.

Churn model + model card

An end-to-end churn workflow with slice analysis, hard-example review and a one-page model card.

Why take this course

Learn the workflow, not just algorithms — baselines, pipelines, validation
Metrics and thresholds tied to real business decisions
Auto-graded labs on every topic
Leakage, fairness and explainability taught as core skills

You will build

A leak-proof scikit-learn pipeline that handles messy real-world data
A depth curve and a forest with a built-in validation score
A metrics report with a recall- or budget-constrained decision threshold
A churn model with a one-page model card

What you can do afterwards

Choose, validate and defend a model with honest uncertainty
Catch leakage and unequal performance before deployment
Communicate model behaviour and limits to non-specialists

Career fit

🧭 Where this fits

Roles whose screened skills map to this course, and the skills it lets you show.

Skills you will build

Bias, leakage & explainability
Supervised & unsupervised learning, evaluation
Supervised & unsupervised ML, evaluation

How to take it

💳 Delivery & fees

One course, four ways to attend. Fees are per course, in rupees excluding 18% GST (the GST-inclusive amount is shown too) with Canadian-dollar fees alongside.

Your fee includes our GPU lab infrastructure — no cloud credits to buy. See how we compare, with sources →