Unifying Data and Models for Cross-domain Personalized Fashion Recommendations

Across industries, people have come to expect highly personalized and dynamic experiences - but for those providing them, managing extensive sets of data across various channels to ensure personalized touchpoints can be an incredibly complex task.
 
In this webinar, we will explore how Stitch Fix evolved its large suite of recommender models into a novel model architecture that unifies data from client interactions to deliver a holistic and real-time understanding of their style preferences. Stitch Fix’s Client Time Series Model (CTSM) is a scalable and flexible sequence-based recommender system that models client preferences over time, based on event data from various sources, to provide multi-domain, channel-specific recommendation outputs. 
 
Data Science Manager, Kevin Zielnicki, will share how the model has enabled Stitch Fix to continuously provide personalized fashion at scale, like no other apparel retailer.

Kevin Zielnicki, Data Science Manager at Stitch Fix

Kevin Zielnicki is Principal Data Scientist, Styling Recommendations Lead at Stitch Fix, where he has worked for over six years. Kevin works on the Product Algorithms team and is interested in the impact recommendation algorithms can have when used as an amplifier for human creativity. Prior to Stitch Fix, Kevin spent time at Silicon Valley Data Science and Seldn in various data science and engineering roles. Kevin holds a PhD in Physics from University of Illinois Urbana-Champaign, where he focused his studies on optical quantum information processing, and a Bachelors of Science in Physics from Harvey Mudd College.

Watch the webinar