Build vs Buy: How Wegmans Built In-House Forecasting Capabilities With PyMC Labs

Opening a new supermarket is a multi-million-dollar bet, and a strong forecast for one site can still hurt the portfolio. Wegmans, with 100-plus stores, chose not to buy a black box. They built their own forecasting capability with PyMC Labs. Hear how the two teams co-designed a Bayesian site-selection model that encodes Wegmans' operator expertise, uses real drive-time trade areas, forecasts in-store and e-commerce demand separately, and measures cannibalization across the network. Built on PyMC, it runs on an analyst's laptop and is owned and extended by Wegmans today. What you'll learn Why Wegmans chose to build forecasting in-house, with a partner, instead of buying How to judge a new site by its effect on the whole portfolio, not just its own forecast How operator knowledge, limited data, and real geography fit in one Bayesian model What it takes to own and extend a model after the partner steps back 📜 Outline of Talk / Agenda: 5 min: Introduction to PyMC Labs and speakers 40 min: Panel discussion 15 min: Q&A \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\- 💼 About the speakers: Dr. Luca Fiaschi (PyMC Labs Partner, Gen AI Vertical) Luca helps organizations unlock the value of data and AI. With 15+ years of experience, he’s led and scaled teams at Mistplay, HelloFresh, Alibaba, and Stitch Fix, driving breakthroughs in personalization, marketing optimization, and causal modeling. He holds a PhD in Computer Science from Heidelberg University. Connect with Luca👉 LinkedIn🧩 Github Ian Costley (Wegmans, Data Scientist Ian Costley is a data scientist in the Customer Insights group at Wegmans Food Markets, serving as a technical lead on applied modeling work. They collaborate across the organization to provide statistical support for decision-making. His interests include probabilistic modeling, inference at scale, and building bespoke models to uniquely fit business problems. Connect with Ian 👉 LinkedIn \