Machine Learning Zoomcamp: A Free 4-Month Course on ML Engineering

Learn machine learning engineering end-to-end, from core models to deploying real applications.

Build regression and classification models in Python, work with key algorithms like linear/logistic regression, decision trees, and deep learning, and then take them to production using Docker, FastAPI, Kubernetes, and AWS Lambda.

Join Slack • #course-ml-zoomcamp Channel • Telegram Announcements • Course Playlist • FAQ • Tweet about the Course

Quick Links

About the Course

Machine Learning Zoomcamp teaches complete machine learning engineering, covering the entire pipeline: from building models with Python to deploying them in production environments.

You'll master the key ML algorithms like linear regression, logistic regression, decision trees, and deep learning with TensorFlow and PyTorch, then learn to containerize with Docker, build APIs with FastAPI, and scale with Kubernetes and AWS Lambda.

Who Should Join

This course is for software engineers, data analysts, and anyone with programming experience who wants to become a machine learning engineer. You don't need any prior machine learning experience; the course starts from the basics.

Prerequisites

You'll need:

• Prior programming experience (at least 1+ year)
• Comfort with command line basics

You don't need any prior experience with machine learning. We'll start from the basics.

Technical setup: for the machine learning modules, you only need a laptop with an internet connection. For the deep learning sections, we'll use cloud resources for more intensive computations.

How to Take the Course

There are two ways to follow the course: live and self-paced.

[!IMPORTANT] "Live cohort" does not mean live classes. All lectures are pre-recorded. "Live" means working alongside others with deadlines, scored homework, a leaderboard, peer review, and a certificate at the end. The live cohort runs once per year (September to December).

To earn a certificate, you'll complete two projects (midterm + capstone, or two capstones) and the required peer reviews during a live cohort.

Self-paced steps:

1. Follow the materials on GitHub
2. Ask questions and share progress in Slack
3. Do the homework (self-checked) and build a project for your portfolio

Syllabus

Module 1: Introduction to Machine Learning

Learn the fundamentals: what ML is, when to use it, and how to approach ML problems using the CRISP-DM framework.

• ML vs rule-based systems
• Supervised learning basics
• CRISP-DM methodology
• Model selection concepts
• Environment setup

Module 2: Machine Learning for Regression

Build a car price prediction model while learning linear regression, feature engineering, and regularization.

• Linear regression (from scratch and with scikit-learn)
• Exploratory data analysis
• Feature engineering
• Regularization techniques
• Model validation

Module 3: Machine Learning for Classification

Create a customer churn prediction system using logistic regression and learn about feature selection.

• Logistic regression
• Feature importance and selection
• Categorical variable encoding
• Model interpretation

Module 4: Evaluation Metrics for Classification

Learn how to properly evaluate classification models and handle imbalanced datasets.

• Accuracy, precision, recall, F1-score
• ROC curves and AUC
• Cross-validation
• Confusion matrices
• Class imbalance handling

Module 5: Deploying Machine Learning Models

Turn your models into web services and deploy them with Docker and cloud platforms.

• Model serialization with Pickle
• FastAPI web services
• Docker containerization
• Cloud deployment

Module 6: Decision Trees & Ensemble Learning

Learn tree-based models and ensemble methods for better predictions.

• Decision trees
• Random Forest
• Gradient boosting (XGBoost)
• Hyperparameter tuning
• Feature importance

Midterm Project

Apply Modules 1-6 in an end-to-end project: pick a dataset, train a model, and deploy it as a web service.

Module 8: Neural Networks & Deep Learning

Introduction to neural networks using TensorFlow and Keras, including CNNs and transfer learning.

• Neural network fundamentals
• PyTorch
• TensorFlow & Keras
• Convolutional Neural Networks
• Transfer learning
• Model optimization

Module 9: Serverless Deep Learning

Deploy deep learning models using serverless technologies like AWS Lambda.

• Serverless concepts
• Deploying Scikit-Learn models with AWS Lambda
• Deploying TensorFlow and PyTorch models with AWS Lambda
• API Gateway

Module 10: Kubernetes & TensorFlow Serving

Learn to serve ML models at scale using Kubernetes and TensorFlow Serving.

• Kubernetes basics
• TensorFlow Serving
• Model deployment and scaling
• Load balancing

Capstone Project 1

A larger end-to-end project at the end of the course, after Module 10.

Capstone Project 2

An optional second capstone, which together with the midterm or first capstone counts toward your two required projects.

Projects

Choose a problem that interests you, find a suitable dataset, develop your model, and deploy it as a web service.

There will be 3 projects:

1. Midterm Project after Module 6: Decision Trees & Ensemble Learning
2. Capstone project 1 at the end of the course, after Module 10: Kubernetes & TensorFlow Serving
3. Capstone project 2 at the end of the course, after Module 10: Kubernetes & TensorFlow Serving

These projects allow you to apply everything you've learned and make a great addition to your GitHub profile and portfolio.

Project Examples from Past Cohorts

A local deployment architecture using Kubernetes with Kind from one of the students' projects

Some of the course projects from past cohorts:

• Blood cell classifier for cancer prediction: an end-to-end tool that segments and classifies blood cells from microscope images to assist in detecting signs of acute lymphoblastic leukemia (ALL)
• Waste classifier: an Xception-based image classifier on ~15,000 waste images, reaching 93.3% test accuracy, and serving predictions via a Flask API packaged in Docker

Certificate

Machine Learning Zoomcamp certificate awarded upon successful completion

To receive a certificate, you'll need to complete and submit two projects:

1. Complete two projects: submit either a midterm project and a capstone project, OR two capstone projects
2. Submit on time: meet the project submission deadlines to qualify for certification
3. Peer review: evaluate and provide feedback on 3 fellow students' projects during the peer review process

See the certificate guide for how the certificate is issued and how to add it to LinkedIn.

Testimonials

Machine Learning Zoomcamp was exhaustive, with very comprehensive content that covered concepts in depth. You can learn everything from the simplest concepts to preparing and deploying an ML model for production. Additionally, the entire community behind this course is highly participative and collaborative. I would like to thank Alexey Grigorev for all the knowledge he shared with us and his team for providing the support we needed to solve each problem we faced.

• Alexander Daniel Rios (Source)

Machine Learning Zoomcamp has been an incredible journey, thanks to the expert guidance of Alexey Grigorev. Hugely grateful to Alexey, Timur, and the entire DataTalksClub team for this course, and to my cohort batchmates for the invaluable support that enriched my learning experience. I'm thankful for this programme, which provided challenging coursework that is taught in a very structured and lucid way. The timely assignments & hands-on projects instill the sense of timely delivery, besides equipping us with practical acumen to solve real-life problems.

• Siddhartha Gogoi (Source)

Balancing the intensive Machine Learning Zoomcamp with my other engagements was no easy task, but the experience deepened my expertise in machine learning engineering, reinforced my passion for ML deployment and cloud technologies, and strengthened my resilience in handling real-world ML challenges. Thank you, Alexey Grigorev, for this course!

• Patrick Edosoma (Source)

Highly recommend the ML Zoomcamp for anyone wanting a structured path to production-ready machine learning. A big thank you - Alexey Grigorev and to the team at DataTalksClub for providing such a well-structured and engaging course.

• Abdiaziz Mohamed (Source 1, Source 2)

A huge thank you to Alexey Grigoriev for creating such an amazing course—and making it free! It's truly inspiring.

• Guilherme Pereira (Source)

Huge thanks to Alexey Grigorev and the DataTalksClub community for the incredible support and clarity throughout. The open-source spirit and collaborative notes made the learning experience even richer.

• Rajendra Rawale (Source)

Community & Support

Getting Help on Slack

Join the #course-ml-zoomcamp channel on DataTalks.Club Slack for discussions, troubleshooting, and networking.

To keep discussions organized:

• Check the FAQ first.
• Follow our question guidelines when posting questions.
• Review the community guidelines.