Chris Moody

I'm an experienced people manager with a history of growing and leading diverse teams of machine learning engineers and scientists that create algorithmic products and recommender systems.

Highlights

At Stitch Fix, I envisioned and created a massively engaging “Tinder for Clothes” app -- Style Shuffle. This key vehicle for data collection strengthened our algorithms and allowed us to enhance our personalized recommendations. As the product took off, I founded and scaled a complementary ML team.

  • Increased engagement by ~30x by shifting 50% of monthly active users to daily active users

  • Increased company revenues by hundreds of millions of dollars via improvements in recommendations, stylist matching, email targeting and other algorithms (see an earnings call)

  • Collected ~10x more data per user which led to more personalized algorithms via "latent style embeddings"

  • Hired and grew a diverse AI team of data scientists and ML engineers from zero to fourteen, eventually including managing managers. I am happy to provide references from managers, reports, and partners.

  • Scaled our production machine learning infrastruture to millions of users and tens of billions of ratings

  • Interviewed (along with our team) for articles in the popular press: WIRED, FastCompany, and Quartz.

  • Developed Style Tyles -- another recsys app I built around dynamic explore & exploit.

As an individual, I have created many side projects, all revolving around creating strong data-driven feedback loops. To get there, I've built engaging full-stack apps with components like engaging game-like frontends, scalable data backends, and model deployment and logging infrastructure.

  • Corner Champ. An app for learning crowd-sourced home valuations. Zillow & competitors are usually off by ~5%, and home buyers placing offers need better home price estimates

  • Hype the Like A Shopify-compatible app that was "Tinder for Product Analytics." It's a free tool for merchants to do zero-risk product exploration, effectively showing images items before stocking.

I've built research- and production-grade machine learning algorithms.

I have spoken at many machine learning conferences, including an invited KDD 2018 (the largest machine learning conference) tutorial on building deep-learning based recommenders in PyTorch

( Made with Carrd )