Speakers:
From Time Series to Delivery Promises: Clustering Postal Codes Beyond Geography at Zalando
Date:
Monday, November 17, 2025
Time:
11:50 am
Summary:
Tight and precise delivery promises are fundamental at Zalando. In some countries, however, our ML models led to unwished overly broad promise windows. Postal codes historically exhibit different delivery behaviors, justifying a move from a country to a regional-level. However, clustering methods are not available for partially observable time series data structures. By extracting empirical probability distributions to cluster postal codes, we obtained regions having tighter promise windows.
Speakers:
Scaling ML and AI in a Dynamic Supply Chain: Lessons from Wayfair
Date:
Monday, November 17, 2025
Time:
12:20 pm
Summary:
How do you apply ML and AI at scale in the messy, high-variance world of e-commerce logistics? In this talk, Gaku Tobinobu shares how Wayfair leverages computer vision, generative AI, and other techniques across supply chain operations—from fulfillment and routing to anomaly detection and customer experience. Grounded in real-world use cases, the session highlights patterns, pitfalls, and practical lessons from building production ML systems.