The program, module by module

1. Module 1 — What Machine Learning Actually Is

   Understand what machine learning adds beyond classic analysis: predicting from past examples rather than describing them.

2. Module 2 — Preparing Data for a Model

   Build meaningful features through feature engineering — ratios, encoding, dates — without causing data leakage.

3. Module 3 — Classification and Regression Models: The Basics

   Choose between classification and regression based on the kind of answer needed, starting with the simplest model.

4. Module 4 — Evaluating a Model: Precision, Recall, Limitations

   Evaluate a model using precision and recall rather than accuracy alone, on data never seen during training.

5. Module 5 — Using Pre-Trained Models

   Use a pre-trained model via an API — text, image — instead of training a custom one, unless a specific need proves it necessary.

6. Module 6 — Business Use Cases: Churn Prediction, Scoring, Recommendation

   Recognize ML business use cases — churn, scoring, recommendation — as support for human decisions, never blind automation.

7. Module 7 — Ethics and Algorithmic Bias

   Detect algorithmic bias by comparing model performance across subgroups, not just on the overall average.

8. Module 8 — When to Call In a Data Scientist

   Recognize the signals that call for a professional data scientist rather than continuing alone.

9. Module 9 — Professional Integration and Certification

   Certification

   Cross-cutting module: CV/portfolio, professional brand, interview practice, and job market activation — specific to this course's real career outcomes. Triggers generation of the final certificate.

How certification works

Three levels, from simplest to most demanding. Each one only claims what it actually verifies.

The distinction is added to your certificate of achievement — it never replaces it: nothing off-platform ever blocks the certificate itself.