Building a Fraud Detection Model with Feature Stores - Includes Shopify Case Study
Offered By: Toronto Machine Learning Series (TMLS) via YouTube
Course Description
Overview
Explore the process of building a real-time fraud detection system using cutting-edge ML data pipeline management tools in this comprehensive workshop. Learn from industry experts as they guide you through the steps of constructing, deploying, and serving real-time data pipelines. Gain insights into the distinctions between traditional feature stores, exemplified by the open-source Feast, and feature platforms like Tecton. Discover common architectural patterns and follow along as the speakers demonstrate model building in three key stages: batch daily computed predictions, online predictions using batch features, and online predictions utilizing real-time features. As a bonus, delve into a case study showcasing how Shopify leverages feature engineering in their ML workflows. This 1-hour and 12-minute session, presented by the Toronto Machine Learning Series (TMLS), features Danny Chiao (Tech Lead, Feast), Eddie Esquivel (Sr. Solutions Architect, Tecton), and Abhin Chhabra (ML Platform Tech Lead, Shopify) sharing their expertise in fraud detection and feature store implementation.
Syllabus
Building a Fraud Detection Model with Feature Stores Includes Bonus Case Study How Shopify uses Fe
Taught by
Toronto Machine Learning Series (TMLS)
Related Courses
Processing Real-Time Data Streams in AzureMicrosoft via edX Gérez des flux de données temps réel
CentraleSupélec via OpenClassrooms Data Streaming
Udacity Taming Big Data with Apache Spark and Python - Hands On!
Udemy Python & Cryptocurrency API: Build 5 Real World Applications
Udemy