Building a recommender system with Amazon ML services
Who is this presentation for?
- Data scientists, machine learning engineers, and data engineers
Level
Description
Karthik Sonti, Emily Webber, and Varun Rao Bhamidimarri introduce you to the Amazon SageMaker machine learning platform and provide a high-level discussion of recommender systems. You’ll dig into different machine learning approaches for recommender systems, including common methods such as matrix factorization as well as newer embedding approaches.
They explore the cold-start problem (recommending new products that don’t have purchase or review history) and approaches that can be used to address this. You’ll also learn how to label datasets using Amazon SageMaker Ground Truth and build a recommendation engine that’s highly customized to your preferences. Using built-in Amazon SageMaker Factorization Machines, BlazingText Word2Vec algorithm and Amazon Personalize, you’ll learn to train and then deploy them to a real-time, product-grade hosted endpoint. Karthik, Emily, and Varun explore natural language generation techniques that can generate new text as product reviews.
Prerequisite knowledge
- General knowledge of Python and recommender systems
- A working knowledge of AWS (useful but not required)
Materials or downloads needed in advance
- A laptop
What you'll learn
- Gain an understanding of recommender systems using Amazon AI/ML services
- Build a working prototype
Karthik Sonti
Amazon Web Services
Karthik Sonti is a partner solution architect at AWS, where he works with GSIs to help accelerate adoption of AWS services with a focus on analytics and machine learning.
Emily Webber
Amazon Web Services
Emily Webber is a machine learning specialist solutions architect at Amazon Web Services (AWS). She guides customers from project ideation to full deployment, focusing on Amazon SageMaker, where her customers are household names across the world, such as T-Mobile. She’s been leading data science projects for many years, piloting the application of machine learning into such diverse areas as social media violence detection, economic policy evaluation, computer vision, reinforcement learning, the IoT, drones, and robotic design. Previously, she was a data scientist at the Federal Reserve Bank of Chicago and a solutions architect for an explainable AI startup in Chicago. Her master’s degree is from the University of Chicago, where she developed new applications of machine learning for public policy research with the Data Science for Social Good Fellowship.
Varun Rao Bhamidimarri
Amazon Web Services
Varun Rao Bhamidimarri is an enterprise solution architect at Amazon Web Services helping customers with adoption of cloud-enabled analytics solutions to meet business requirements.
Presented by
Elite Sponsors
Strategic Sponsors
Zettabyte Sponsors
Contributing Sponsors
Exabyte Sponsors
Content Sponsor
Impact Sponsors
Supporting Sponsor
Non Profit
Contact us
confreg@oreilly.com
For conference registration information and customer service
partners@oreilly.com
For more information on community discounts and trade opportunities with O’Reilly conferences
strataconf@oreilly.com
For information on exhibiting or sponsoring a conference
pr@oreilly.com
For media/analyst press inquires