Next-Gen Restaurant Recommendation with Generative Modeling and Real-Time Features

April 17, 2026

2026年4月17日

Yicheng Chen

Yicheng Chen

Staff ML Engineer

Staff ML 工程师

Peng Chen

Peng Chen

Senior Staff ML Engineer

资深 ML 工程师

Nikat Patel

Nikat Patel

Senior Machine Learning Engineer

高级机器学习工程师

2+

2+

Introduction

介绍

The homefeed is the primary gateway for millions of Uber Eats users worldwide, serving as the central hub where hunger meets discovery. For people using Uber Eats, a well-optimized feed reduces cognitive load and helps them find their next meal with ease. For merchants, it’s a critical platform for visibility and growth. As the scale of our offerings grows—expanding from local favorites to grocery, alcohol, and retail—the homefeed’s role as a personalized discovery engine becomes even more vital to the overall experience.

homefeed 是全球数百万 Uber Eats 用户的主要入口，作为饥饿与发现相遇的中心枢纽。对于使用 Uber Eats 的人来说，一个优化良好的 feed 可以减少认知负担，并帮助他们轻松找到下一餐。对于商家来说，它是一个关键的可见性和增长平台。随着我们产品规模的扩大——从本地美食扩展到杂货、酒类和零售——homefeed 作为个性化发现引擎的作用对整体体验变得更加重要。

Powering this experience is our recommendation model, an intelligent layer that synthesizes billions of signals—from real-time behavioral cues to geographic context—to rank the optimal options for every session. To keep pace with this increasing complexity and scale, we’ve fundamentally overhauled our modeling architecture. This blog explores how we modernized the Uber Eats feed recommendation system using behavioral sequences, transformer architectures, and near-real-time features, while establishing a roadmap toward generative recommendation models.

为这一体验提供动力的，是我们的推荐模型，这是一个智能层，它综合了数十亿个信号——从实时行为线索到地理上下文——来为每个会话排名最佳选项。为了跟上这种日益增加的复杂性和规模，我们彻底改造了我们的建模架构。本文探讨了我们如何使用行为序列、transformer 架构和近实时特征来现代化 Uber Eats 信息流推荐系统，同时为生成式推荐模型制定了路线图。

Figure 1: Uber Eats home feed experience (mobile app).

图 1：Uber Eats 首页流体验（移动应用）。

From Statistics-Based Features to User Behavioral Sequence Features

从基于统计的特征到用户行为序列特征

For years, our homefeed DeepCVR model relied primarily on aggregate statistics and hand-crafted features to predict Uber Eats user affinity for a given merchant. While effective at a baseline level, the...