Data Products at Scale: Credit Card Fraud Detection for Over 800,000 Businesses
It is a long road from having an amazing first model to deploying it in production and maintaining its efficiency over time. Finding extremely rare events in near real time adds additional complexity. I will talk about how at Shopify, one of the leading e-commerce platforms, we are making orders safe to fulfill for over 800,000 merchants operating in 175 different countries. I will present the steps we took to deploy, maintain, and improve our ML pipeline for credit card fraud detection.
Nevena Francetic is a Data Science Manager at Shopify, an e-commerce platform. Her main focus is on industrial applications of machine learning for financial products. Her team protects merchants by detecting credit card fraud and building products around fraud protection. Nevena has a PhD in Mathematics from the University of Toronto.