About Course
Machine learning is more than calling .fit(). In this hands-on course you will learn how real teams frame problems, prepare features, choose and tune models, and prove that a model is good enough to ship.
Every module is built around a realistic dataset, from predicting customer churn to forecasting demand, so you finish with a portfolio of projects you can show to employers or clients.
What you will learn
- Framing business questions as supervised and unsupervised problems
- Feature engineering and pipelines with scikit-learn
- Model evaluation, cross-validation and avoiding data leakage
- Gradient boosting, random forests and when to use them
- Explaining predictions to non-technical stakeholders
- Packaging and deploying a model behind a simple API
Course Content
Thinking Like an ML Engineer
-
From business question to ML problem
-
Setting up a reproducible project
-
Exploring the churn dataset
Features & Pipelines
Models & Evaluation
From Notebook to Production
Student Ratings & Reviews
No Review Yet