The JD.com Infrastructure team won the SIGIR 2018 e‑commerce competition by developing a multi‑level deep‑learning model that tackled severe class imbalance, vocabulary drift, and hierarchical labeling, boosting F1 from 0.74 to 0.84 and earning paper acceptance at the SIGIR conference.
The article explains how JD.com’s Tongtian Tower platform enables non‑technical operators to create activity pages through a React‑based visual editor, detailing its background, design goals, component architecture, template definition, data handling, quality assurance measures, and future development directions.
This article describes how JD built a multi‑regional, ten‑thousand‑node Hadoop ecosystem, unified resource management with YARN, introduced a three‑level Router scheduling layer, optimized performance, and integrated deep‑learning frameworks to achieve high availability, cost efficiency, and scalable big‑data processing.
This interview chronicles Gaofei Gao’s nine‑year journey at JD.com, from joining the company after the Qianxun acquisition, leading the launch of the POP platform, migrating to Java, and later driving the B2B middle‑office in Chengdu while fostering a high‑tempo, team‑first culture.
This article details the comprehensive integration of JD's Service Market and Plugin Market, covering system architecture, data and process fusion, service workflow unification, transaction handling, and front‑back separation redesign to achieve a unified, high‑performance e‑commerce platform.
The talk outlines JD.com Mall’s PMO evolution from 2012 to 2018, detailing its shift to a full‑lifecycle management approach, the development of a T‑shaped project‑manager capability model, performance assessment mechanisms, and strategies for open empowerment amid VUCA challenges.
The article recounts JD.com architect Li Biao’s transition from traditional software to internet engineering, detailing how he resolved a critical Oracle database outage by building a task‑driven engine, applied component‑based design in the 7FRESH project, and shares his insights on system architecture, team building, and continuous learning.
JD.com's Archimedes is a data center operating system that provides one-click scaling, intelligent scheduling, mixed deployment, and multi-site active-active capabilities, significantly improving resource utilization and reducing IT costs.
The article shares practical guidance for JD.com’s R&D middle‑platform project managers, emphasizing internal and external cultivation, responsibility, humility, passion, empathy, professional project‑management skills, and effective communication to influence cross‑functional teams and drive successful delivery of business requirements.
Learn step‑by‑step how to use Python’s urllib and BeautifulSoup CSS selectors to fetch JD.com product details—such as name, link, image, and price—by constructing the search URL, parsing the HTML source, and extracting the desired information with concise code examples.
This tutorial shows how to use Python's urllib and XPath to accurately extract product details such as name, link, image, and price from JD.com search results, offering a clearer alternative to regular expressions and BeautifulSoup.
This tutorial shows how to use Python's urllib and BeautifulSoup libraries to encode search keywords, request JD.com pages, parse the HTML tree, and reliably extract product names, links, images, and prices, offering a simpler alternative to complex regular‑expression scrapers.
The article chronicles JD.com’s middle‑platform R&D PMO from its 2012 founding through phases of following, driving, and leading, detailing team growth, agile scaling challenges, PMI China collaboration, performance models, award wins, and strategic goals for 2018.
This tutorial shows how to build a keyword‑driven web crawler for JD.com using Python's urllib for URL encoding and opening, combined with powerful regular expressions to accurately extract product information such as dog food listings, and explains how to extend the scraper for multi‑page data collection.
He Xiaofeng, JD Mall Infrastructure chief architect, discusses his role in building a real‑time computing platform, applying streaming frameworks, machine learning, and knowledge‑graph techniques to product data mining, improve search accuracy, and outline future research directions.
This article explains how JD.com’s network team continuously optimizes its large‑scale infrastructure, designs effective monitoring strategies, implements practical monitoring solutions, and outlines future directions to improve network availability, fault detection, and operational efficiency across data centers and the internet backbone.
The article details JD.com’s large‑scale, automated server operating‑system deployment process for the 11.11 shopping festival, describing the challenges of tight timelines, massive equipment volumes, the development of an automated deployment platform, and the operational improvements achieved through process optimization and 24/7 support.
This article examines JD.com’s technical strategies for the 2023 Double‑11 shopping festival, detailing dynamic load‑balancing and rate‑limiting mechanisms, evolving fault‑drill practices, and AI‑powered product and marketing enhancements that together ensure high‑concurrency stability and improved user experience.
The article shares JD.com Mall R&D Management expert Qian Zhilin’s three‑year experience, detailing four stages of project management—from early follow‑up and coordination to guidance, planning, and the evolution toward project‑set management—offering practical lessons for R&D and product teams.
At the 15th China ECR Conference in Hangzhou, JD.com’s Vice President Ma Song highlighted the company’s technology‑driven twelve‑year roadmap, showcasing smart supply‑chain solutions powered by big data and artificial intelligence that improve forecasting, pricing, inventory, and collaboration while enhancing the retail experience.
JD.com's JData Algorithm Competition concluded with record-breaking participation, awarding 600,000 yuan in prizes and offering special employment opportunities to top performers, while showcasing how AI and big data enhance e-commerce experiences.
The JD Data Algorithm Competition aims to help shoppers overcome decision paralysis by using advanced algorithms to match users with products they'll love, featuring diverse participants from students to professionals competing for prizes and potential real-world implementation.
A public course live stream featuring industry experts discussing AI applications in advertising technology, attracting over 8,000 viewers and 60,000 likes, highlighting the integration of machine learning and data mining in ad optimization.
This article details how JD.com rebuilt its 2016 homepage using the Athena front‑end engineering suite, covering overall architecture, unified development workflow, performance and experience optimizations, reliability mechanisms, data‑driven monitoring, and future directions such as static pre‑loading and architectural upgrades.
This article explains how JD.com designs a multi‑layer data storage architecture—using MySQL for core metadata, HBase and MongoDB for comment text, Solr/Elasticsearch for indexing, and Redis for caching—to handle billions of daily review requests with high performance and availability.
The article details the development, architecture, and operational practices of JD.com’s CMS platform, covering its three evolutionary stages, front‑back separation, dynamic data types, disaster‑recovery mechanisms, intelligent product selection, and lessons learned from large‑scale deployment.
This article chronicles JD.com's transition from commercial to open‑source databases, detailing MySQL's rapid growth, the development of the JMySQL automation platform, and future directions for database design, security, monitoring, and performance optimization in large‑scale e‑commerce environments.
The article details JD.com's technical strategies for scaling product detail pages under massive traffic, covering service decomposition, KV‑based dynamic rendering with Nginx+Lua, unified service gateways, isolation, caching, monitoring, degradation, and performance testing to achieve sub‑50 ms response times.
This article explains JD.com’s search update cycles, indexing rules for SKUs and product attributes, common reasons products disappear or drop in rank, and practical optimization tips covering high‑relevance categories, text relevance, pricing models, title strategies, and traffic entry points.
The article explains how JD.com leverages big‑data and personalized recommendation algorithms across PC and mobile platforms, detailing its recall and ranking models, efficiency analysis, weekly algorithm iterations, and future AI‑driven optimizations that together contribute about 10% of its orders.
This article dissects JD.com’s Qinglong logistics system, detailing its O2O strategy, big‑data‑driven pre‑sorting, AI algorithms, GIS integration, and the evolution from version 1.0 to 3.0, highlighting how these technologies enable ultra‑fast, agile supply‑chain operations.
JD.com’s management philosophy, based on Liu Qiangdong’s view that team quality determines success, is explained through four core HR frameworks—Capability‑Values matrix, ABC authority hierarchy, 8‑12‑20 staffing ratios, and the 2N rule—detailing how the company selects, evaluates, and retains its 75,000‑plus workforce.