Retail data science, in production
I’m a Senior Data Scientist who specializes in retail. Over the past several years I’ve built machine learning and AI systems for two of the largest retailers in the United States, from the forecasting and optimization models that decide what gets made, how much of it, and where it goes, to the recommender systems that shape what shoppers see online.
I’m currently at VF Corporation, supporting its top three brands, Vans, The North Face, and Timberland, on demand forecasting and inventory optimization. Before VF I spent four years at Kohl’s: I started in supply chain on ETA forecasting, moved into e-commerce to build the recommender systems behind product recommendations on Kohls.com, and then returned to supply chain for demand forecasting, optimization, and allocation.
That blend of customer-facing and behind-the-scenes retail work is the part I enjoy most. Outside of industry I’m an Adjunct Professor at the University of Denver, teaching graduate courses in Machine Learning and Database Systems, a published contributor on Towards Data Science and KDnuggets, and a guest on the DAMN Podcast, where I talked about my path from professional soccer to data science.
Areas of expertise
The retail problems I spend my time on, from the warehouse to the website.
Demand Forecasting
Time-series and machine learning models that predict what customers will buy, so brands can plan production and buys with confidence.
Inventory Optimization & Allocation
Deciding how much stock to hold and where to send it, balancing service levels against carrying cost across the network.
Recommender Systems
The personalization models behind product recommendations in e-commerce, from candidate generation through ranking.