Building a recommender system with Amazon ML services

Karthik Sonti (Amazon Web Services), Emily Webber (Amazon Web Services), Varun Rao Bhamidimarri (Amazon Web Services)

1:30pm–5:00pm Tuesday, September 24, 2019

Location: 1A 21

Data Science, Machine Learning, & AI

Secondary topics: Cloud Platforms and SaaS, Deep dive into specific tools, platforms, or frameworks

Average rating:

(3.67, 3 ratings)

Who is this presentation for?

Data scientists, machine learning engineers, and data engineers

Level

Intermediate

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.