Author

JD Retail Technology

Official platform of JD Retail Technology, delivering insightful R&D news and a deep look into the lives and work of technologists.

804

Articles

Likes

1.8k

Views

Comments

Latest from JD Retail Technology

100 recent articles max

JD Retail Technology

Mar 25, 2026 · Databases

How JD.com Scaled POP Order Elasticsearch to Handle Billions of Orders

This article analyzes the challenges of JD.com's POP order Elasticsearch storage—including data skew, oversized shards, frequent updates, and high maintenance costs—and details the multi‑layered architectural redesign that introduced tenant isolation, dual‑hash routing, differentiated shard strategies, and a dual‑active physical foundation to achieve high performance, scalability, and availability.

Data PartitioningElasticsearchOrder Management

0 likes · 16 min read

How JD.com Scaled POP Order Elasticsearch to Handle Billions of Orders

JD Retail Technology

Mar 3, 2026 · Frontend Development

How JD’s Order Module Achieved One‑Code‑Three‑Platform Success with Taro

This article details JD.com’s six‑month engineering effort to refactor its high‑traffic order module into a single Taro codebase that runs on Android, iOS and HarmonyOS, covering business background, preparation, multi‑mode adaptation, core challenges, quality assurance, efficiency gains and the resulting business impact.

HarmonyOSOrder ModulePerformance Monitoring

0 likes · 21 min read

How JD’s Order Module Achieved One‑Code‑Three‑Platform Success with Taro

JD Retail Technology

Jan 30, 2026 · Artificial Intelligence

How JD’s 9N‑LLM Engine Powers Scalable Generative Recommendation at Industrial Scale

The article details JD Retail’s 9N‑LLM unified training engine—supporting TensorFlow and PyTorch, GPU and NPU, and both traditional and generative recommendation scenarios—explaining its architecture, high‑throughput sample engine, distributed sparse embedding system, five‑stage pipeline, UniAttention accelerator, and reinforcement‑learning capabilities that together enable TB‑scale data, B‑scale dense parameters, and efficient RL training for real‑world recommendation services.

Distributed TrainingGPU/NPUUniAttention

0 likes · 26 min read

How JD’s 9N‑LLM Engine Powers Scalable Generative Recommendation at Industrial Scale

JD Retail Technology

Jan 22, 2026 · Operations

How JD Global Sales Boosted UI Test Speed by 100× with a Three‑Layer Multilingual Testing Framework

This article outlines JD Global Sales' multilingual testing challenges, the three‑layer interface‑page‑user‑flow testing architecture, automation and AI‑driven strategies that delivered over 100× UI efficiency and 70%+ API gains while paving the way for continuous globalized quality assurance.

AutomationMultilingual Testinge-commerce

0 likes · 13 min read

How JD Global Sales Boosted UI Test Speed by 100× with a Three‑Layer Multilingual Testing Framework

JD Retail Technology

Jan 13, 2026 · Backend Development

Deep Dive into Kafka, RocketMQ, and JMQ Storage Architectures

This article compares the storage models, data organization, indexing, read/write processes, and performance trade‑offs of three major message queues—Kafka, RocketMQ, and JMQ—providing detailed technical insights for architects and engineers making storage‑related design decisions.

Backend EngineeringJMQKafka

0 likes · 16 min read

Deep Dive into Kafka, RocketMQ, and JMQ Storage Architectures

JD Retail Technology

Jan 8, 2026 · Artificial Intelligence

Uni-Layout: Unified Cross-Task Layout Generation with Human-Aligned Evaluation

Uni-Layout introduces a unified layout generation framework that consolidates diverse design tasks, leverages multimodal large language models for flexible generation, and aligns outputs with human perception through a novel human‑feedback dataset (Layout‑HF100k) and a dynamic margin preference optimization (DMPO) evaluator.

ACM MultimediaHuman Feedbackdynamic margin optimization

0 likes · 11 min read

Uni-Layout: Unified Cross-Task Layout Generation with Human-Aligned Evaluation

JD Retail Technology

Jan 5, 2026 · Big Data

How JD’s Data Lake Uses Hudi LSM‑Tree to Power Near‑Real‑Time Data Assets

The article details JD’s data lake architecture, its 500 PB scale, self‑developed Hudi extensions—including LSM‑Tree‑based MoR tables, custom indexing, IO optimizations, Flink stream scheduling, and NativeIO SDK—along with benchmarks, community contributions, and future roadmap for real‑time big‑data processing.

HudiLSM‑Treebig data

0 likes · 19 min read

How JD’s Data Lake Uses Hudi LSM‑Tree to Power Near‑Real‑Time Data Assets

JD Retail Technology

Dec 25, 2025 · Backend Development

How We Rebuilt a 15‑Year‑Old Review Platform: From Monolithic Code to a Scalable DDD‑Driven Architecture

This article details the complete redesign of a fifteen‑year‑old e‑commerce review system, covering its legacy pain points, the strategic choice of a full‑stack reconstruction using Domain‑Driven Design, the new layered micro‑service architecture, data migration tactics, operational challenges, organizational safeguards, and the measurable performance gains achieved after launch.

ArchitectureDDDMicroservices

0 likes · 35 min read

How We Rebuilt a 15‑Year‑Old Review Platform: From Monolithic Code to a Scalable DDD‑Driven Architecture

JD Retail Technology

Dec 11, 2025 · Artificial Intelligence

How GIN-Based Cohort Modeling Boosts Cold-Start CTR Prediction by 2%

This article explains a SIGIR 2025 paper that tackles cold‑start click‑through‑rate prediction in JD's ad system by using a Graph Isomorphism Network‑based cohort modeling framework, detailing its three‑module architecture, extensive experiments on public and industrial datasets, and a live deployment that achieved a 2.13% CTR lift.

CTR predictionGinRecommendation Systems

0 likes · 9 min read

How GIN-Based Cohort Modeling Boosts Cold-Start CTR Prediction by 2%

JD Retail Technology

Dec 4, 2025 · Artificial Intelligence

Twin Networks Reveal How to Optimize Data Mixtures for Large Language Models

This article presents TANDEM, a bi‑level data‑mixture optimization framework that uses twin networks to automatically adjust domain‑specific training data ratios, offering theoretical guarantees, broader applicability, and significant performance gains across pre‑training, fine‑tuning, and e‑commerce product‑understanding tasks.

NeurIPSbi-level optimizationdata mixture optimization

0 likes · 6 min read

Twin Networks Reveal How to Optimize Data Mixtures for Large Language Models