Machine Learning Zoomcamp

A free 4-month course on ML Engineering: learn to build and deploy practical machine learning models from regression and classification to deep learning.

Join the 2025 Cohort Watch on YouTube

About ML Zoomcamp

This is a practical course where you’ll learn to build and deploy machine learning systems. We focus on the engineering side from training models to getting them to work in production.

Prerequisites

  • Prior programming experience (at least 1+ year)
  • Comfort with command line basics
  • No prior ML experience required

What You’ll Learn

  • Core ML algorithms and when to use them
  • Data preparation and feature engineering
  • Model evaluation and selection
  • Deployment with Flask, Docker, and cloud platforms
  • Using Kubernetes for ML model serving
  • MLOps practices

Course Modules

Module 1: Introduction to Machine Learning

Learn the fundamentals of ML and the CRISP-DM framework.

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

Module 2: Machine Learning for Regression

Build a car price prediction model.

  • Linear regression
  • Exploratory data analysis
  • Feature engineering
  • Regularization techniques

Module 3: Machine Learning for Classification

Create a customer churn prediction system.

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

Module 4: Evaluation Metrics for Classification

Learn proper model evaluation techniques.

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

Module 5: Deploying Machine Learning Models

Turn models into web services.

  • Model serialization
  • Flask web services
  • Docker containerization
  • Cloud deployment

Module 6: Decision Trees & Ensemble Learning

Improve predictions with tree-based methods.

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

Midterm Project

Apply your skills in a complete ML project.

Module 7: Neural Networks & Deep Learning

Introduction to deep learning.

  • Neural network fundamentals
  • TensorFlow & Keras
  • Convolutional Neural Networks
  • Transfer learning

Module 8: Serverless Deep Learning

Deploy models using serverless technologies.

  • AWS Lambda for ML
  • TensorFlow Lite
  • API Gateway

Module 9: Kubernetes & TensorFlow Serving

Scale ML models with Kubernetes.

  • TensorFlow Serving
  • Model deployment and scaling
  • Load balancing

Module 10: KServe (Optional)

Advanced model serving for production.

Capstone Project

Build and deploy an end-to-end ML system.

Table of contents