General info 

This is a one-day training course. Select the desired start date at the top right of the screen for practical information regarding the training (location, price, registration, etc.).

Course overview

In this intermediate-level course, you will learn how to solve a real-world use case with Machine Learning (ML) and produce actionable results using Amazon SageMaker. This course walks through the stages of a typical data science process for Machine Learning from analyzing and visualizing a dataset to preparing the data, and feature engineering. Individuals will also learn practical aspects of model building, training, tuning, and deployment with Amazon SageMaker. Real life use case includes customer retention analysis to inform customer loyalty programs.

Who should attend this training

This course is intended for:

• Developers
• Data Scientists

Course Objectives

In this course, you will learn how to:

• Prepare a dataset for training
• Train and evaluate a Machine Learning model
• Automatically tune a Machine Learning model
• Prepare a Machine Learning model for production
• Think critically about Machine Learning model results

Prerequisites

We recommend participants to have the following prerequisites:

• Familiarity with Python programming language
• Basic understanding of Machine Learning

Course Content

Module 1: Introduction to Machine Learning

• Types of ML
• Job Roles in ML
• Steps in the ML pipeline

• Training and Test dataset defined
• Introduction to SageMaker
• Demo: SageMaker console
• Demo: Launching a Jupyter notebook

• Business Challenge: Customer churn
• Review Customer churn dataset

• Demonstration: Loading and Visualizing your dataset
• Exercise 1: Relating features to target variables
• Exercise 2: Relationships between attributes
• Demo: Cleaning the data

• Types of Algorithms
• XGBoost and SageMaker
• Demonstration: Training the data
• Exercise 3: Finishing the estimator definition
• Exercise 4: Setting hyper parameters
• Exercise 5: Deploying the model
• Demonstration: Hyper parameter tuning with SageMaker
• Demonstration: Evaluating Model Performance

• Automatic hyper parameter tuning with SageMaker
• Exercises 6-9: Tuning Jobs

• Deploying a model to an endpoint
• A/B deployment for testing
• Auto Scaling
• Demonstration: Configure and Test Auto Scaling
• Demonstration: Check hyper parameter tuning job
• Demonstration: AWS Auto Scaling
• Exercise 10-11: Set up AWS Autoscaling
• Cost of various error types
• Demo: Binary Classification cutoff

• Cost of various error types
• Demo: Binary classification cutoff

• Accessing Amazon SageMaker notebooks in a VPC
• Amazon SageMaker batch transforms
• Amazon SageMaker Ground Truth
• Amazon SageMaker Neo