This article explains how to protect sensitive user data in e‑commerce chatbot logs by routing all service logs through LoongCollector, pushing them to Alibaba Cloud SLS, and applying built‑in and keyword‑based mask functions so that privacy is preserved without breaking business logic.
This article breaks down the new 2025 Internet Platform Enterprise Tax Information Reporting Regulation, explains its regulatory and supportive goals, identifies the three types of affected entities, and provides a step‑by‑step guide for platforms to redesign systems, automate compliance processes, and avoid fines while fostering fair competition and social equity.
The article recounts how a risk‑control algorithm engineer progressively refined a generic large language model through four stages of prompt engineering—defining roles, dimensions, structured I/O, business rules, behavior fingerprints, and a dual‑hypothesis decision framework—to transform it into a precise e‑commerce fraud detection expert.
This article reveals how vague or incomplete requirement documents can cost companies hundreds of thousands, outlines three common fatal mistakes with concrete examples and corrective guidelines, and provides a practical checklist to rescue and improve future specifications.
This article presents JD Retail's award‑winning, data‑driven inventory selection and allocation framework that combines machine‑learning‑based demand forecasting, heuristic selection algorithms, and an end‑to‑end multi‑task learning model to improve fulfillment rates, reduce stock‑out loss, and lower inventory transfer costs in a large‑scale e‑commerce supply chain.
This article details JD Retail's award‑winning, data‑driven inventory selection and allocation algorithms, explains their mathematical models, heuristic and end‑to‑end learning solutions, presents experimental results on real‑world data, and quantifies the operational gains achieved after deployment.
The article outlines the role of the content compliance domain in e‑commerce, detailing user‑facing issues, business responsibilities, challenges in detection and mitigation, and technical solutions such as comparable‑price models, large‑scale price prediction, and merchant outreach, while also offering personal growth advice for compliance engineers.
This article outlines the evolution of e‑commerce data‑warehouse governance—from current challenges in data scale, quality, cost and security, through four developmental stages, to concrete solutions and future directions for stable, efficient, and secure data assets.
This document outlines a complete test plan, testing strategies, resource allocation, schedule, risk management, acceptance criteria, and deployment procedures for an e‑commerce Double‑11 promotion, emphasizing functional, interface, and performance testing to ensure system stability and high‑quality user experience.
This article details the multi‑stage evolution of JD's search Explore‑Exploit (EE) system—covering an adaptive dynamic detection model, scenario‑modeling upgrades, end‑to‑end scoring and insertion consistency, and context‑aware brand/store dimension detection—demonstrating how each iteration improves result diversity, user experience, and key online metrics while maintaining search efficiency.
This article provides a comprehensive overview of the end‑to‑end Chinese internet payment architecture, illustrating the flow from e‑commerce platforms through checkout, third‑party payment channels, banking networks, clearing and settlement, and detailing the roles of components such as the cashier, transaction core, membership, payment, accounting and clearing systems.
This case study details Baidu Hotel’s design process for a price‑comparison feature, outlining market background, user research, strategic touchpoints, competitive analysis, and three implementation phases that together enhanced perception, built cognition, and reinforced memory, ultimately improving conversion rates.
This article examines the rapid rise of independent e‑commerce sites, compares their user‑experience, navigation, transaction flow and visual design with traditional platforms, and shares practical design tips and common pitfalls based on recent market data and Baidu's new SaaS solution.
This article introduces the fundamentals of recommendation systems, explains Zhuanzhuan's main recommendation scenarios and pipeline, and details three graph embedding methods—DeepWalk, node2vec, and EGES—along with their practical implementations in recall and coarse‑ranking stages.
This article presents a comprehensive overview of conversion‑rate (CVR) optimization for Alitrip’s travel recommendation platform, detailing the challenges of extremely sparse user feedback, the design of item, user, query and context features, and a series of model‑level and loss‑function techniques—including generic‑label modeling, global‑transaction modeling, ESMM, rank‑loss approximations, and multi‑task CTR auxiliary training—to improve both CTR and CVR performance in high‑ticket‑price scenarios.
The article explains how rapid internet growth created information overload, leading to concise summary services, and how recent AI advances—especially large language models like GPT‑3—enable platforms such as JD.com to automatically generate high‑quality, multimodal product copy that drives sales and supports diverse creative tasks.
This case study details JD.com's 11.11 home‑appliance campaign, covering project background, brand goals, consumer‑centric design thinking, visual creativity with interactive scenes, front‑end performance optimizations, AB‑testing results, and insights on turning design into measurable commercial value.
During JD's 11.11 promotion, the team adopted the AI‑powered low‑code tool Deco to generate personalized event pages, replacing manual coding and low‑code platform workflows, achieving a 48% efficiency gain while detailing the workflow, component integration, code generation, data handling, and observed limitations.
Alibaba’s eight‑year Double 11 journey illustrates how the company tackled exponential business growth by inventing high‑availability middleware, precise capacity planning, unit‑based deployment, online stress testing, hybrid‑cloud elasticity, and intelligent runtime control to balance throughput, cost, and user experience during the midnight peak.
This article introduces the fundamentals of user profiling, explains tag types and their business value, and demonstrates a data‑driven e‑commerce case study that analyzes gender, age, region, marital status, education, profession, product preferences, purchase timing, and price sensitivity to guide targeted promotion strategies.
JD Logistics architect Chen Haolong detailed the design, scalability strategies, and operational practices behind the billion‑level asynchronous messaging system that powered JD.com’s massive 11.11 shopping festival, revealing how the platform handled unprecedented traffic and ensured reliability.
Tony Hsieh, the Harvard‑educated founder of Zappos, turned a $160,000 startup into a $12 billion Amazon acquisition by pioneering customer‑centric culture, innovative return policies, and unconventional management practices that reshaped online shoe retail and inspired countless entrepreneurs.
This article explains how Alibaba’s Tmall leveraged intelligent UI—combining AI-driven recommendation, UI digitization protocols, and integrated front‑end development—to enhance user experience and increase traffic efficiency during the Double‑11 shopping festival.
This article explains how the Alibaba interactive team built a custom EVA‑based front‑end solution—including page rendering infrastructure, a specialized development system, and global stability measures—to achieve ultra‑fast loading, zero‑fault operation, and record‑breaking participation for the Double‑11 "Super Star Cat" campaign.
This article analyzes why the used‑car search conversion is low, reconstructs user search scenarios from query data, categorizes search intents, identifies pain points across the search funnel, and proposes product‑level redesigns and recommendation strategies to educate vague users and deliver more precise results.
The Xianyu interest‑tagging system profiles post‑95 users by matching expert and hot‑search keywords to product text, weighting user actions with a TF‑IDF‑based behavior‑statistics pipeline, producing over twenty tags that cover more than half the target cohort and have already doubled click‑through rates for interest‑aligned live streams.
This article explains how to boost new‑user purchase conversion on e‑commerce landing pages by applying five behavioral conditions—cue, reaction, evaluation, ability, and timing—through the CREATE model, offering practical design guidelines, information hierarchy, and timing tactics backed by psychological research.
This article explains how Alibaba B2B leverages knowledge‑graph technology—from its historical roots in knowledge engineering and expert systems to modern semantic‑web models, extraction pipelines, reasoning methods, storage solutions, and representation learning—to improve search, recommendation, and scene‑based procurement incentives in e‑commerce platforms.
This article examines the rapid rise of live‑ecommerce during the 618 shopping festival, explains why the “live + ecommerce” model demands robust backend, streaming and CDN infrastructure, and details Tencent Cloud’s architectural solutions—including media processing, low‑latency protocols, bandwidth optimization and anti‑attack measures—to support massive concurrent traffic.
Facing unprecedented traffic during the 2020 618 shopping festival, JD Health’s product R&D team implemented comprehensive rehearsals, stress testing, architecture reviews, dual‑channel risk controls, and 24‑hour monitoring to ensure system stability and rapid response for its health‑care e‑commerce platforms.
This article reviews academic research on uncertainty‑based promotion strategies, explaining their types, psychological mechanisms, suitable scenarios, and practical design guidelines to help e‑commerce operators create more effective, curiosity‑driving campaigns.
JD.com's Smart Supply Chain Y Business Management team collaborated across divisions to implement AI‑driven demand forecasting, automated replenishment, micro‑service architecture, and real‑time monitoring, enabling precise inventory control, cost reduction, and seamless 11.11 promotion fulfillment through integrated planning, pricing, and fulfillment innovations.
The article details JD.com's internally developed distributed search engine and recommendation platform, their new architectures, deep‑learning‑driven ranking and recall models, component‑based deployment, extensive performance testing, and coordinated operations that powered the massive 11.11 shopping event.
JD.com's Retail Technology and Data Platform orchestrated a full‑chain, four‑entry‑point stress test for the 11.11 shopping festival, introduced an upgraded Forcebot traffic‑recording tool, and implemented a "Quality Month" with ten safeguards to ensure system stability and prevent incidents during the massive sales event.
This article presents a Transformer‑based framework that simultaneously generates visually compatible outfits and personalizes recommendations by leveraging multimodal item embeddings and user behavior, achieving significant gains in compatibility prediction, fill‑in‑the‑blank accuracy, and click‑through rate on Alibaba's iFashion platform.
The article analyzes platform product growth by examining Douyin's user expansion tactics and JD's e‑commerce strategies, covering platform value, growth strategies, network effects, single‑ and double‑sided drives, local network effects, growth challenges, and corresponding solutions.
This paper presents a sequence‑to‑sequence model that fuses product‑detail tables with customer comments, using gated multimodal attention, copy mechanisms and reinforcement learning to automatically produce high‑quality, context‑aware replies for e‑commerce platforms, and validates the approach with extensive experiments on a large Taobao dataset.
This article explains how graph embedding techniques, including a BSP‑based distributed LINE implementation and a cross‑category probabilistic graph model, are applied to improve the diversity and relevance of bundle (凑单) recommendations during large‑scale shopping events.
The project, initiated by Tsinghua University's School of Economics and Management in partnership with JD.com, analyzes the online art auction market, proposes a balanced commercial model using new technologies such as blockchain, and documents the successful launch of a student‑created artwork auction that generated nearly 200 pieces and set the stage for future collaborations.
This article details Alibaba's Intelligent Writer system, which leverages AI models like PairXNN and deep generation networks to automatically create short copy, benefit points, and rich visual lists for Taobao, achieving significant click‑through improvements during the 2017 Double‑11 shopping festival.
This article explains the principles, algorithms, and practical challenges of search autocomplete (query suggestion), covering popularity‑based models, time‑sensitive methods, user‑aware and context‑aware approaches, data pipelines, indexing, ranking, personalization, and evaluation techniques used in e‑commerce search systems.
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.
This article explains the design of JD’s flash‑sale (抢购) system, covering its business model, core Redis‑based inventory management, Lua scripting for atomic stock deduction, rate‑limiting, asynchronous logging with JMQ, and fail‑over strategies to ensure high‑concurrency reliability.
This article explains how JD.com derives the displayed "JD price" from base prices and promotion rules using a real‑time pricing system built on Nginx, Redis clusters, and Tomcat, detailing the data flow, caching strategy, and disaster‑recovery mechanisms.
The article explains how JD.com designed and deployed a multi‑center transaction architecture, using a high‑performance data bus and strict consistency and routing controls, to handle the massive traffic spikes of the 11.11 e‑commerce event while ensuring scalability and disaster recovery.
JD.com’s senior engineers detail how a combination of massive Docker‑based cloud migration, multi‑center transaction architecture, intensive 60‑second recovery drills, and AI‑driven personalization via the JD Brain enabled the platform to handle the unprecedented traffic and data demands of the 11.11 shopping festival.
