BestHub
Sign in
JD Tech Talk
JD Tech Talk
Sep 9, 2025 · Artificial Intelligence

How JD’s Dynamic Re‑Ranking Model Boosted Search Relevance and Won SIGIR 2024

The author recounts how, by modeling user intent with a multi‑layer Gaussian‑based PODM‑MI framework and addressing a novel ‘sand‑glass’ bottleneck in RQ‑VAE semantic identifiers, JD’s search ranking achieved significant UCVR gains, annual order increases of over ten million, and a SIGIR 2024 paper acceptance.

E-commerce AIRecommendation SystemsSIGIR
0 likes · 8 min read
How JD’s Dynamic Re‑Ranking Model Boosted Search Relevance and Won SIGIR 2024
JD Cloud Developers
JD Cloud Developers
Sep 9, 2025 · Artificial Intelligence

How JD’s PODM‑MI Framework Revolutionized E‑commerce Search Ranking

This article recounts a JD engineer’s journey from theory to practice, detailing the development of the PODM‑MI re‑ranking framework, its three‑layer distribution‑based design, the discovery of a novel SID bottleneck, and the resulting multi‑million‑order impact validated at SIGIR 2024.

E-commerce AIRe‑rankingSIGIR
0 likes · 8 min read
How JD’s PODM‑MI Framework Revolutionized E‑commerce Search Ranking