Feature Store Meetup #12 with Findify

This is a free, online event taking place over Zoom.
Link to join live: https://us02web.zoom.us/j/87327737557

-- Agenda --

When you see a long list of things like posts in a social network feed, products in an e-commerce store, or book recommendations in an era of informational overdose, it’s much easier to switch to cat videos than to scroll to the next page of the list. Relevancy and ordering are crucially important if you want to improve both your business metrics and make customers’ journey easier, so visitors will see things they are looking for in front of their eyes, and not on page 7.

In this talk, Roman and Vsevolod will tell you a story of building Metarank, an open-source personalization tool that can optimize the ordering of items to boost important business metrics like engagement, CTR, and conversion. Metarank uses an internal embedded feature store under the hood, and we’re going to discuss why we made a decision to reinvent the wheel and not stick to existing solutions.

-- About the speakers --

Roman Grebennikov - ML Engineer at Findify
Roman is working on search personalization and recommendations at Findify. He is a pragmatic fan of functional programming, learn-to-rank models and performance engineering.

Vsevolod Goloviznin - Head of Product at Findify
A software engineer in the past, who switched tracks to work closely with customers and products. Has multi-year experience of communicating with customers to understand what they really want and translating this information to engineers as a Head of Product.

-- About the organizers --

This global meetup is organized by https://featurestore.org, a voluntary educational program concerned with disseminating information about Feature Stores for machine learning.

If you want to submit a talk: https://featurestore.org/submit-a-talk/