Machine Learning Zoomcamp

🎓 New cohort starting September 2025! Register

Free Course

Master ML Engineering
From Zero to Deployment

A comprehensive 4-month course that takes you from beginner to advanced ML engineer. Learn the fundamentals of ML, from regression and classification to deployment and deep learning.

Register Learn More
👥 10,000+ students
⏰ 4 months of content
⭐ 10.4k GitHub stars
Python scikit-learn TensorFlow Keras XGBoost Docker Kubernetes AWS

What You'll Learn

A comprehensive curriculum covering the entire machine learning lifecycle

Machine Learning Foundations

  • Python programming for ML
  • Data manipulation with Pandas
  • Numerical computing with NumPy
  • Data visualization best practices
  • Statistical analysis fundamentals

Core ML Algorithms

  • Linear & Logistic Regression
  • Decision Trees & Random Forests
  • Gradient Boosting with XGBoost
  • Model evaluation metrics
  • Cross-validation techniques

Deep Learning

  • Neural Networks fundamentals
  • TensorFlow & Keras
  • Convolutional Neural Networks
  • Transfer Learning
  • Model optimization techniques

Model Deployment

  • RESTful API development
  • Docker containerization
  • Cloud deployment (AWS)
  • Kubernetes orchestration
  • CI/CD pipelines

Best Practices

  • ML system design patterns
  • Code organization & testing
  • Model monitoring
  • Performance optimization
  • Production-ready code

Career Development

  • Portfolio building
  • Real-world projects
  • Industry best practices
  • Technical documentation
  • Collaboration skills

Technologies You'll Master

A comprehensive tech stack for end-to-end machine learning development and deployment

01

Machine Learning Algorithms

Master the fundamentals of ML algorithms and their implementation

Python

Python

The foundation of data science and machine learning development

Core Language
Jupyter

Jupyter

Interactive computing environment for development and experimentation

Development
NumPy

NumPy

Linear algebra and numerical computing for ML algorithms

Data Processing
Pandas

Pandas

Data manipulation, analysis, and feature engineering

Data Processing
Seaborn

Matplotlib & Seaborn

Data visualization and statistical graphics

Visualization
Scikit-learn

Scikit-learn

Implementation of various ML algorithms and evaluation metrics

Machine Learning
TensorFlow

TensorFlow

Open-source framework for deep learning and neural networks

Deep Learning
Keras

Keras

High-level neural network API for rapid deep learning development

Deep Learning
XGBoost

XGBoost

Gradient boosting framework for advanced ensemble learning

Machine Learning
02

Model Deployment

Learn to deploy ML models to production environments

Flask

Flask

Web framework for creating ML model APIs

Web Framework
Docker

Docker

Containerization for ML model deployment

DevOps
Kubernetes

Kubernetes

Container orchestration for scaling ML applications

DevOps
AWS Lambda

AWS Lambda

Serverless computing for ML model serving

Cloud
TensorFlow Lite

TensorFlow Lite

Optimized framework for mobile and edge devices

Mobile & Edge
TensorFlow Serving

TensorFlow Serving

Production system for ML model deployment

Deployment
Pipenv

Pipenv

Python dependency and environment management

Development

Prerequisites

Programming Experience

At least 1 year of programming experience in any language

  • Basic understanding of functions and classes
  • Experience with data structures
  • Familiarity with version control (Git)

Command Line Basics

Comfort with basic terminal operations

  • Navigation and file operations
  • Running scripts and commands
  • Package installation

ML Knowledge

No prior machine learning knowledge required!

  • We'll teach you ML from scratch
  • Step-by-step approach
  • Focus on practical applications

Meet the requirements? Take the next step in your ML career!

Begin Your Journey

Course Syllabus

A comprehensive curriculum covering the entire machine learning lifecycle

Module 1

Introduction to Machine Learning

  • ML vs Rule-Based Systems
  • Supervised Learning
  • CRISP-DM Framework
  • Model Selection Process
  • Environment Setup
  • Homework
Module 2

Machine Learning for Regression

  • Car Price Prediction Project
  • Exploratory Data Analysis
  • Linear Regression Basics
  • Feature Engineering & Regularization
  • Homework
Module 3

Machine Learning for Classification

  • Churn Prediction Project
  • Feature Selection & Encoding
  • Logistic Regression
  • Model Interpretation
  • Homework
Module 4

Evaluation Metrics

  • Accuracy, Precision, Recall
  • ROC Curves & AUC
  • Cross-Validation
  • Homework
Midterm Project

End-to-End ML Solution

Apply your knowledge from modules 1-4 to create a complete machine learning solution.

  • Select and prepare a dataset
  • Perform EDA and feature engineering
  • Train and evaluate models
  • Document your approach and findings
Module 5

Deploying ML Models

  • Saving & Loading Models
  • Flask API Deployment
  • Docker & Virtual Environments
  • Cloud Deployment (AWS)
  • Homework
Module 6

Decision Trees & Ensemble Learning

  • Decision Trees
  • Random Forest & Gradient Boosting
  • Model Selection & Hyperparameter Tuning
  • Homework
Module 7

Neural Networks & Deep Learning

  • TensorFlow & Keras
  • Convolutional Neural Networks
  • Transfer Learning
  • Model Optimization & Regularization
  • Homework
Module 8

Serverless Deep Learning

  • Introduction to Serverless
  • AWS Lambda & TensorFlow Lite
  • API Gateway
  • Homework
Module 9

Kubernetes & TensorFlow Serving

  • TensorFlow Model Serving
  • Kubernetes Basics
  • Deploying ML Models to Kubernetes
  • Homework
Module 10

KServe (Optional)

  • Advanced model serving with KServe
  • Production ML systems
Capstone Project

Production ML System

Build a complete production-ready machine learning system.

  • End-to-end ML pipeline implementation
  • Model deployment to cloud
  • API development and containerization
  • Performance monitoring and optimization
  • Documentation and presentation

Ready to dive into machine learning?

Start Learning Today

How You'll Learn

Our comprehensive approach combines theory, practice, and community support

01

Theory Meets Practice

Each concept is followed by hands-on practice. You'll learn by doing, not just watching.

02

Interactive Learning

Video lectures are paired with code demos, bringing complex concepts to life through practical examples.

03

Weekly Assignments

Reinforce your learning with practical homework assignments that challenge and inspire.

04

Portfolio Project

Cap off your learning with an end-to-end project that showcases your new skills to potential employers.

05

Vibrant Community

Join DataTalks.Club on Slack to connect with peers, share insights, and get support when you need it.

Homework & Support System

Get regular feedback and help when you need it

Weekly Homework & Leaderboard

To reinforce your learning, we offer regular homework assignments, reviewed and scored by industry professionals. Your scores are added to an anonymous leaderboard, creating friendly competition among course members and motivating you to do your best.

Anonymous leaderboard with scored homework

Anonymous leaderboard tracking homework scores

Weekly Cadence

Regular assignments to keep you on track

Friendly Competition

Anonymous leaderboard to track progress

Comprehensive Support System

We've built a multi-layered support system to ensure you never get stuck:

FAQ Documentation

Quick answers to common questions in our comprehensive FAQ section

Browse FAQ

Live Office Hours

Regular Q&A sessions with instructors for immediate help

Community Support

24/7 access to our Slack community for technical questions

Join Slack Community
A screenshot of an FAQ document

Comprehensive FAQ documentation

Build Your ML Portfolio

Create real-world projects that showcase your skills to potential employers

Course Projects

As a machine learning engineer, personal projects are crucial for job interviews and demonstrating practical experience. You'll complete two major projects during the course:

  • Midterm Project: Choose your own problem, find a dataset, and develop a complete ML solution
  • Capstone Projects: Build and deploy a production-ready ML model as a web service
Featured Student Project
Screenshot of Pastor Soto's project

Top Project Spotlight

Pastor Soto's project ranked #1 in the 2022 cohort leaderboard, demonstrating excellence in both implementation and deployment.

Bonus Opportunities

  • Optional Research Article:

    Explore advanced topics beyond the curriculum and write a technical article about your findings.

  • Public Portfolio:

    All projects are featured in our annual leaderboard and make excellent additions to your GitHub profile.

  • Community Recognition:

    Top projects are showcased to our community of 10,000+ data practitioners.

View 2022 Project Leaderboard

Meet Your Instructor

Alexey Grigorev

Alexey Grigorev

Founder of DataTalks.Club

A seasoned software engineer and data scientist with over 10 years of engineering and 6 years of ML experience, Alexey specializes in bringing data science projects from early prototypes to production. His expertise spans problem identification, data collection, model creation, deployment, and maintenance.

Professional Background

  • Lead Data Scientist at OLX Group (Berlin) - Built large-scale ML systems processing 250+ images/second
  • Data Scientist at Simplaex - Developed ML infrastructure processing 3+ billion events daily
  • Data Scientist at Searchmetrics (Berlin)
  • Research positions at TU Berlin, Boston University Cognitive Neuroscience Lab

Publications & Achievements

  • Author of "Mastering Java for Data Science" (2017) and "TensorFlow Deep Learning Projects" (2018)
  • Kaggle Competition Master with multiple top-10 finishes, including 1st place in NIPS'17 Criteo Challenge
  • Published researcher with papers in SIGIR and WSDM
  • IT4BI Master's graduate (ULB, UFRT, TU Berlin)
Python & Java Expert ML Systems Design Kaggle Master Published Author Community Builder
DataTalks.Club LinkedIn GitHub Google Scholar Kaggle

What Our Students Say

If anyone is looking for a great hands-on ML course with amazing theory and practical component, the ML Zoomcamp is for you. It's all free and gives you access to not only the highly technical and up-to-date content but to a diverse and helpful community as well. You can find a lot of useful information from the dynamic Slack conversations.

Anurag Singh Waliya Senior Machine Learning Engineer, Dru AI
View on LinkedIn

A huge thank you to Alexey Grigorev, the team and the entire community for their support and their guidance. Over the course of the program, I explored a wide range of topics—from data manipulation, visualization, and applying ML algorithms (scikit-learn) to neural networks and deep learning (TensorFlow, Keras). We also covered essential deployment techniques using Docker, Flask, and automated scaling including Kubernetes and serverless deep learning with TensorFlow Lite. Working on hands-on projects was incredibly valuable and helped me learn the core principles of machine learning in real-world scenarios. If you're looking to dive into ML, I highly recommend checking out the ML Zoomcamp!

Mohammed Amine DERKAOUI Data Engineer at Trimane
View on LinkedIn

This journey has been an incredible experience—diving deep into the fundamentals of machine learning, building real-world projects, and collaborating with an amazing community of learners. From data preprocessing to model deployment, this program has strengthened my practical skills and problem-solving abilities. A big thank you to the organizers, mentors, and fellow participants who made this learning experience truly enriching!

Henry (Chisom) Nduka Software Developer at Creven Tech
View on LinkedIn

Join thousands of successful students

Register Now

Watch & Learn

Get to know our course better through these videos

Live Q&A

Get answers to the most common questions about the ML Zoomcamp

Launch Stream

Watch our course introduction and learn what to expect

Learn in Public

Share your journey, build your presence, earn recognition

Why Learn in Public?

  • Earn Extra Points

    Get bonus points for sharing your progress, insights, and projects online

  • Build Your Portfolio

    Create valuable content that showcases your skills and knowledge

  • Increase Visibility

    Get noticed by social media algorithms and reach a broader audience

  • Network Growth

    Connect with individuals and organizations in the data science community

Extract from Shawn Wang's article about learning in public

Inspired by Shawn @swyx Wang's approach to learning in public

Leaderboard showing bonus points for learning in public

Previous cohort leaderboard showing bonus points earned through public learning

Everyone has something valuable to contribute, regardless of their expertise level

Start Your Learning Journey

Learn with Our Community

You'll be part of DataTalks.Club - a thriving community of 73,000+ data practitioners

A Supportive Learning Environment

As part of this course, you'll join a vibrant community of like-minded individuals passionate about data science and machine learning. Our active Slack community provides:

  • Enhance your skills through peer learning
  • Connect with peers who share your passion
  • Get help and support when you need it
  • Build lasting friendships and professional connections

All course participants get immediate access to our active Slack community

Join Slack Community • Telegram Announcements • Course Playlist • FAQ
Course channel in our Slack community

Active discussions in our ML Zoomcamp Slack channel

10,000+ Community Members
24/7 Active Support
Global Community
100% FREE

Start Learning Today!

Choose your learning path: self-paced or join our next cohort in September 2025

Self-Paced Learning

Start Immediately
  • Instant access to all course materials
  • Complete curriculum on GitHub
  • Access to all recorded sessions
  • Learn at your own pace
Access Materials Now

Join 10,000+ students learning ML!

Live Cohort (Sept 2025)

Certificate Opportunity
  • All self-paced features
  • Regular live office hours
  • Structured timeline with deadlines
  • Certificate upon completion
  • Peer learning & project reviews
Register

Next cohort starts September 2025

Why is this course free?

We believe in making quality education accessible to everyone. This course is part of our mission to democratize machine learning education and build a global community of data practitioners. Your success is our success!

Frequently Asked Questions

How is the course structured?

The course runs for 4 months and includes pre-recorded videos, live office hours, hands-on projects, and a vibrant community. You'll need around 10 hours per week for coursework and projects.

How can I start learning?

You have two options:

  • Self-paced learning: Start immediately! All course materials are pre-recorded and freely available on GitHub. You can learn at your own pace.
  • Live cohort: Join our next cohort starting September 15, 2025 to learn with peers, participate in live sessions, and earn a certificate. Subscribe to calendar updates.

What's included in the live cohort?

  • Regular live office hours with instructors
  • Structured learning path with deadlines
  • Peer interaction and community support
  • Opportunity to earn a certificate
  • Access to all recorded sessions and office hours

Note: Even if you're self-paced, you still have access to all course materials and recordings!

How do I get certified?

To earn a certificate, you'll need to:

  1. Join a live cohort
  2. Complete 2 out of 3 projects:
    • Midterm project
    • Capstone project (includes deploying a model as a web service)
  3. Review 3 peers' projects by the deadline

Important: Projects must be completed individually, and you must be part of a cohort to be eligible for certification.

Can I join after the course has started?

Yes! While you might miss some homework deadlines, you can still join and get certified by completing the required projects. All course materials remain accessible.

What Python knowledge do I need?

You should be familiar with basic Python concepts like variables, libraries, and Jupyter notebooks. If you need to brush up, we recommend taking our Introduction to Python course first.

What technical setup do I need?

For machine learning modules, you only need a laptop with internet connection. For deep learning sections, we'll use cloud resources (like Saturn Cloud) for more intensive computations.

What's the balance between theory and practice?

The course is heavily focused on practical implementation. We cover theoretical concepts at an intuitive level, emphasizing hands-on coding and real-world applications over mathematical derivations.

How can I engage with the community?

Join our active Slack community, participate in office hours, and share your learning journey on social media with #mlzoomcamp. You can earn extra points for sharing your learning experience publicly.

Sponsors & Supporters

A special thanks to our course sponsors for making this initiative possible!

About DataTalks.Club

DataTalks.Club is a global online community of data enthusiasts. It's a place to discuss data, learn, share knowledge, ask and answer questions, and support each other.

Website • Join Slack Community • Newsletter • Upcoming Events • Google Calendar • YouTube • GitHub • LinkedIn • Twitter

Free Education

Courses and online events at no cost

Global Community

Connect with 73,000+ data professionals worldwide

Career Growth

Practical skills and networking opportunities