Learning at Serving Time (LAST): An Online Learning Approach for Real‑Time Re‑ranking in Recommendation Systems

This article introduces LAST, a novel online learning method that updates ranking models instantly at serving time without waiting for user feedback, addressing the latency and stability challenges of real‑time re‑ranking in industrial recommendation pipelines and demonstrating its superiority through offline and online experiments.

Online LearningReal-Timemachine learning

0 likes · 11 min read

Learning at Serving Time (LAST): An Online Learning Approach for Real‑Time Re‑ranking in Recommendation Systems

JD Retail Technology

Aug 18, 2023 · Artificial Intelligence

Overview of Recommendation Systems: Definitions, Architecture, Recall, Ranking, and Re‑ranking

This article provides a comprehensive overview of recommendation systems, covering their definition, basic framework, request flow, AB testing, recall strategies (both non‑personalized and personalized), collaborative‑filtering methods, vector‑based retrieval, wide‑and‑deep models, and the MMR re‑ranking algorithm with code examples.

Vector Retrievalcollaborative filteringmachine learning

0 likes · 14 min read

Overview of Recommendation Systems: Definitions, Architecture, Recall, Ranking, and Re‑ranking