May 22, 2026•1 min read•from InfoQ

Uber Improves Restaurant Recommendations Using Real-Time Signals and Listwise Ranking

Uber updates its Uber Eats Home Feed recommendation system using near real-time user sequence features and a Generative Recommender model. The system evolves from hand-crafted features to transformer-based sequence modeling, reduces feature freshness from 24 hours to seconds, and shifts from pointwise scoring to listwise GenRec for improved contextual ranking and real-time personalization.

By Leela Kumili

Want to read more?

Check out the full article on the original site

View original article→

Tagged with

#real-time data collaboration

#real-time collaboration

#generative AI for data analysis

#natural language processing for spreadsheets

#financial modeling

#cloud-based spreadsheet applications

#Excel alternatives for data analysis

#financial modeling with spreadsheets

#generative AI automation

#rows.com

#Uber Eats

#recommendation system

#Generative Recommender

#real-time signals

#real-time personalization

#user sequence features

#contextual ranking

#transformer-based sequence modeling

#listwise GenRec

#feature freshness