EMER: End-to-End Multi-Objective Ranking That Transforms Short-Video Recommendations

EMER, Kuaishou’s end‑to‑end multi‑objective ensemble ranking framework, replaces handcrafted scoring formulas with a transformer‑based model that learns comparative preferences, integrates normalized rank features, optimizes relative satisfaction and multi‑dimensional proxy metrics, and dynamically balances objectives via a self‑evolving advantage evaluator, delivering significant online gains.

Recommendation SystemsTransformermachine learning

0 likes · 17 min read

EMER: End-to-End Multi-Objective Ranking That Transforms Short-Video Recommendations

21CTO

Sep 7, 2021 · Artificial Intelligence

Designing Effective Short‑Video Recommendation Systems: Goals, Multi‑Objective Modeling, and Long‑Term Value

This article examines the rapid growth of short‑video platforms, outlines the core problems a recommendation system must solve for users, creators, and advertisers, describes the end‑to‑end pipeline, explores multi‑objective modeling and fusion techniques, and discusses long‑term value estimation for sustained user engagement.

AIlong-term valuemulti-objective ranking

0 likes · 8 min read

Designing Effective Short‑Video Recommendation Systems: Goals, Multi‑Objective Modeling, and Long‑Term Value

Baidu Geek Talk

Sep 6, 2021 · Artificial Intelligence

Short Video Recommendation System Design: Baidu Haokan Video Practice

The article outlines Baidu Haokan’s short‑video recommendation architecture, describing how a unified ranking pipeline uses user‑interest signals, multi‑objective MMOE and deep‑fusion models, and long‑term value estimation to balance personalized user experience, creator exposure, and advertiser goals across billions of daily video plays.

BaiduMMoElong-term value

0 likes · 8 min read

Short Video Recommendation System Design: Baidu Haokan Video Practice

DataFunTalk

Feb 24, 2021 · Artificial Intelligence

Multi‑Objective Ranking in Kuaishou Short‑Video Recommendation: System Design and Online Results

This article details Kuaishou's multi‑objective ranking pipeline for short‑video recommendation, covering manual score fusion, GBDT ensemble, Learn‑to‑Rank, online auto‑tuning, ensemble sorting, reinforcement‑learning rerank, and on‑device rerank, and reports their impact on DAU, watch time and user interaction.

Kuaishoumachine learningmulti-objective ranking

0 likes · 21 min read

Multi‑Objective Ranking in Kuaishou Short‑Video Recommendation: System Design and Online Results