Google, IBM & Meta Certificates — 40% Off for a Limited Time
Live Online Classes in Design, Coding & AI — Small Classes, Free Retakes
Overview
Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
Learn to build a complete e-commerce recommendation system using Kumo AI's Graph Neural Network service in this comprehensive 55-minute tutorial. Discover how to leverage Kumo AI to abstract away the complexity of building GNNs for predictive analytics, transforming what typically takes months of data wrangling and model training into a streamlined process. Work with real H&M transaction data containing 33 million records to create a recommendation engine capable of predicting customer lifetime value for 30-day periods, generating personalized product recommendations, and forecasting purchase behavior to identify active customers. Master the setup and configuration of Kumo AI, explore data connectors and BigQuery integration, understand graph construction principles, and utilize Predictive Query Language (PQL) for advanced analytics. Gain hands-on experience with personalized recommendation algorithms, purchase volume prediction models, and practical implementation strategies for deploying machine learning solutions in production environments.
Syllabus
00:00 Kumo AI and GNNs
07:39 Kumo Setup
12:17 Kumo Connectors
14:45 Getting Data into BigQuery
20:39 Building the Graph in Kumo
28:34 Predictive Query Language PQL
35:01 Personalized Product Recommendations
38:44 Predicting Purchase Volume
41:44 Making Predictions with Kumo
27:10 Analysis and Prediction with Kumo
52:36 When to use Kumo
Taught by
James Briggs