Tagged articles
user behavior
51 articles · Page 1 of 1
The article explains why a closed‑loop feedback system is essential for recommendation engines, describes the end‑to‑end architecture from client‑side event collection through gateways, message queues, preprocessing, data warehousing, and traceability, and details how the resulting signals drive user profiling, feature generation, sample creation and model training while addressing practical engineering challenges.
Model TrainingRecommendation Systemdata pipeline
0 likes · 47 min read


SuanNiMar 31, 2026 · Industry Insights
Anthropic’s March 2026 Economic Index analyzes over two million Claude.ai and API conversations, showing how usage is spreading from high‑skill professional tasks to everyday activities, how model choice varies by task value, and how longer‑time users achieve higher success rates, highlighting emerging AI adoption trends and skill gaps.
AI ProductivityAnthropicClaude
0 likes · 15 min read

This article walks through a complete data‑driven study of Taobao app user actions, using SQL and Python to ingest 2 million records, applying the AARRR funnel and RFM segmentation to quantify churn, retention, conversion rates, and to propose data‑backed marketing tactics.
AARRRPythonRFM
0 likes · 25 min read


Amap TechDec 3, 2025 · Artificial Intelligence
Gaode’s G‑Action framework combines large‑language‑model pre‑training with fine‑tuned generative recommendation to predict a user’s immediate action and destination, transforming static map services into a dynamic, context‑aware experience and delivering measurable gains in click‑through and engagement metrics.
AIMap Serviceslarge language model
0 likes · 15 min read

A recent OpenAI‑partnered research paper analyzing billions of ChatGPT interactions reveals that 70% of conversations are non‑work related, three core use cases cover 80% of demand, asking for advice now outpaces doing tasks, and the user base is becoming younger, more gender‑balanced, and globally diverse.
AI usageChatGPTdigital transformation
0 likes · 12 min read

This article analyzes a JD e‑commerce dataset using Python and MySQL to calculate key metrics such as PV, UV, conversion rates, attrition, daily activity, hourly trends, user‑behavior funnels, purchase intervals, retention rates, product sales, and RFM segmentation, and then offers data‑driven recommendations to improve traffic, conversion, and user loyalty.
PythonRFMSQL
0 likes · 37 min read

A comprehensive glossary for e‑commerce product managers that defines key metrics such as GMV, SKU, UV, CVR, AOV, CPC, and models like RFM and AARRR, while highlighting common pitfalls and practical strategies for data‑driven decision making.
GlossaryMetricsconversion rate
0 likes · 9 min read


21CTOApr 22, 2025 · Artificial Intelligence
Sam Altman revealed that excessive politeness toward ChatGPT, such as saying “please” and “thank you,” can drive up server workload and electricity use, potentially costing OpenAI tens of millions of dollars, while highlighting broader concerns about AI energy consumption and user behavior.
ChatGPTartificial intelligenceenergy consumption
0 likes · 5 min read

The article explains how Douyin's recommendation system uses machine‑learning and deep‑learning models to predict user actions, assign value weights, and dynamically adjust scores, highlighting both its efficiency in large‑scale content distribution and its inherent limitations compared to human understanding.
AIRecommendation Systemdeep learning
0 likes · 7 min read

The fourth round of supermarket checkout simulation reveals hidden complexities such as receipt‑paper replacement, cash‑change shortages, and cart blockages, leading to a set of core performance‑testing design principles that emphasize realistic user behavior modeling, data volume, environment fidelity, diversity, and iterative feedback.
Data VolumeSimulationenvironment configuration
0 likes · 6 min read

This article presents the latest advances from the Chinese Academy of Sciences in graph machine learning for user behavior risk control, introducing the LOGIN framework that leverages large language models as consultants to iteratively enhance GNN training, and demonstrates its effectiveness through extensive experiments on homogeneous and heterogeneous graph benchmarks.
Graph Neural NetworksRisk Controllarge language models
0 likes · 14 min read

This article explains the concepts, formulas, and step‑by‑step implementation of a user‑retention analysis model, covering both Hive‑based offline processing and ClickHouse‑accelerated real‑time queries, complete with SQL examples, architecture diagrams, and practical optimization tips.
ClickHouseHiveRetention Analysis
0 likes · 19 min read

The article explains retention analysis models, their importance for user loyalty, outlines offline Hive architecture, then shows how ClickHouse’s retention() function and columnar storage dramatically speed up multi‑day retention calculations, providing SQL examples and practical guidance for product analytics.
ClickHouseData ModelingHive
0 likes · 17 min read

This study analyzes JD e‑commerce operational data from February to April 2018, employing Python and SQL to compute key metrics such as PV, UV, conversion rates, attrition, purchase frequency, time‑based behavior, funnel analysis, retention, product sales, and RFM segmentation, and provides actionable recommendations for improving user engagement and sales performance.
MetricsRFMSQL
0 likes · 30 min read

This article examines various user behavior recording methods—including WebRTC video capture, canvas-based screenshot recording, and DOM snapshot recording with rrweb—detailing their technical implementations, advantages, limitations, and suitable application scenarios for product analysis, debugging, and automated testing.
RecordingVueWebRTC
0 likes · 28 min read

This article explains ten data‑analysis techniques for enhancing user experience—such as behavior tracking, A/B testing, sentiment analysis, and personalization—and provides concrete SQL code snippets that illustrate how to import, query, filter, sort, aggregate, join, update, delete, and back up data in relational databases.
A/B testingSQLUser Experience
0 likes · 8 min read

This article explains the concept of data tracking (埋点), outlines its key application scenarios such as exposure, click, and page‑event tracking, describes the end‑to‑end workflow from requirement gathering to deployment and post‑analysis, and summarizes the practical “seven‑word” checklist for successful implementation.
data collectiondata trackingproduct analytics
0 likes · 12 min read

The article examines repurchase strategies for game item recommendations, analyzing various recommendation scenarios, their specific challenges, item classification based on purchase density and repurchase rates, and practical guidelines for applying the strategy across permanent shop, limited‑time gift packs, and refreshable recommendations.
game itemsproduct managementrecommendation
0 likes · 11 min read

This article presents a comprehensive Python-based analysis of a large game dataset (2.29 million records, 109 fields), covering user registration trends, payment rates, ARPU/ARPPU calculations, level‑based spending behavior, and consumption patterns of resources and acceleration items, with visualizations and actionable conclusions.
Game AnalyticsPandasPython
0 likes · 11 min read

This presentation explains how leveraging user behavior sequences with supervised and unsupervised deep learning models, including end‑to‑end and two‑stage architectures, improves transaction fraud detection by identifying distinct patterns of account takeover and stolen‑card activities and outlines the engineering deployment pipeline.
Embeddingdeep learningfraud detection
0 likes · 12 min read


21CTOMar 30, 2022 · Big Data
This article analyzes 2 million Taobao app user‑behavior records using AARRR funnel metrics and RFM segmentation, revealing daily and hourly usage patterns, conversion bottlenecks, product‑search mismatches, and offering data‑driven marketing recommendations to boost retention and sales.
AARRRRFMSQL
0 likes · 25 min read


DevOpsDec 30, 2021 · Frontend Development
This article explains why front‑end tests that concentrate on implementation details become fragile and time‑consuming, and argues for writing tests that mimic real user interactions using Testing Library, while recognizing that many small functions lack independent business value and should be tested at the UI level instead of as isolated unit tests.
Frontend TestingReact HooksUnit Tests
0 likes · 9 min read


政采云技术Dec 16, 2021 · Big Data
This article explains the concept of event tracking (埋点), its importance for capturing user behavior, outlines the four‑module architecture of a tracking system, compares code‑based, visual and full tracking methods, describes data models, storage, management, and presents a practical case study with analysis techniques.
AnalyticsBackendbig data
0 likes · 15 min read


58UXDDec 6, 2021 · Fundamentals
This article explains how designers can shift from macro metrics like DAU to analyzing raw user interaction data, infer user psychology, reconstruct real usage scenarios, and identify optimization opportunities through concrete examples and step‑by‑step methods.
UX designbehavioral analyticsdata analysis
0 likes · 8 min read

The article describes Alibaba Moments’ advertising creative optimization platform, which uses hybrid bandit models that combine visual‑aware ranking priors with exploration‑exploitation algorithms such as Thompson Sampling and LinUCB to dynamically select whole creatives or individual elements, improving click‑through rates and mitigating cold‑start challenges.
Algorithmic OptimizationHybrid Modelsadvertising creatives
0 likes · 14 min read

DoKit’s one‑machine‑multi‑control lets an Android host device manage slave devices over a LAN without extra permissions or code intrusion, dramatically streamlining functional regression and compatibility testing while supporting user‑behavior recording, and is slated for open‑source release with future extensions to Flutter and Web.
AndroidDoKitcross‑platform
0 likes · 8 min read

This article surveys recent research on extracting and expanding hot topics from short texts by constructing user‑behavior graphs, applying graph‑embedding techniques, and leveraging multi‑task learning to improve recommendation relevance, timeliness, and cold‑start handling in large‑scale platforms.
artificial intelligencegraph embeddingknowledge graph
0 likes · 12 min read

This article analyses the unique challenges of stranger‑social platforms such as Tinder and Tantan, exploring business models, user behavior, network effects, gender dynamics, data collection, algorithmic matching, risk control, and system architecture to guide product strategy and optimization.
data analysismatching algorithmsproduct strategy
0 likes · 30 min read

The article explains how to build a unified user‑behavior data collection platform that standardizes event definitions, front‑end reporting, and back‑end storage using Kafka pipelines and Elasticsearch, enabling comprehensive analysis of user interactions across Android, iOS, and web clients.
BackendElasticsearchKafka
0 likes · 12 min read


政采云技术May 17, 2020 · Frontend Development
This article describes how the frontend team designed and implemented a comprehensive user behavior data collection and analysis platform, covering its business value, overall architecture, SDK-based data gathering, event interception, processing pipelines, analytics dashboards, and practical insights for product and operations teams.
AnalyticsSDKdata collection
0 likes · 15 min read

This article explains the purpose and types of data metrics, outlines a logical framework for analyzing e‑commerce performance from traffic to behavior to transaction, and details ten key metrics—including GMV, conversion rate, UV value, click‑through and exposure rates—along with practical interpretation tips.
AnalyticsGMVconversion rate
0 likes · 12 min read

This article explains how to choose and combine appropriate evaluation metrics for recommendation systems by considering the specific scenario, business model, offline versus online testing, ecosystem balance, and user behavior, providing practical methods and a concise summary of common metric types.
AIMetricsevaluation
0 likes · 18 min read

This article systematically describes the challenges, design principles, modeling methods, layered architecture, implementation steps, and standards used in building a comprehensive user behavior data warehouse for 58.com, highlighting practical experiences and future improvement directions.
Data ModelingETLbig data
0 likes · 11 min read

The article explores the historical origins of the QWERTY layout, how its design intentionally slowed typing to prevent mechanical jams, why alternative ergonomic keyboards failed to replace it, and the psychological habit‑formation factors that keep users locked into this seemingly inefficient standard.
QWERTYergonomicshabit formation
0 likes · 8 min read

By applying sequence pattern mining and unsupervised clustering to Xianyu’s massive event logs, the study abstracts high‑level user behaviors, discovers frequent subsequences, uncovers unknown fraudulent account patterns, expands known fraud cohorts with 99 % precision, and enables richer analyses such as PCA‑based cross‑group comparisons.
big dataclusteringdata mining
0 likes · 8 min read

The article explains how data serves as a critical asset for recommendation systems, outlining the necessary steps from understanding business problems and data dimensions to collection, cleaning, integration, and analysis, while distinguishing explicit and implicit user feedback and emphasizing data quality, timeliness, and relevance.
ETLdata collectiondata quality
0 likes · 11 min read

This article presents an overview of Ctrip's travel recommendation system, detailing its architecture, user‑behavior analysis, product catalog handling, various recall strategies, ranking methods—including machine‑learning models like XGBoost—and future directions toward deeper AI and NLP integration.
CtripRankingRecommendation System
0 likes · 9 min read


网易UEDCMar 11, 2019 · Product Management
This article explains why products lose users, defines the Aha Moment as the pivotal instant of value discovery, and provides a step‑by‑step framework—including hypothesis formulation, cohort analysis, and optimal action thresholds—to capture that moment and boost retention through data‑driven growth experiments.
Aha Momentcohort analysisuser behavior
0 likes · 13 min read


58UXDNov 2, 2018 · Product Management
This article explores how everyday location migrations reveal deeper user motivations, detailing Baidu Maps' evolution from precise navigation to multi‑service 4K, 3D, and AOI maps, while examining mixed travel modes, environmental variables, and design strategies for tool‑type products.
Location ServicesMixed Travel Modesmap design
0 likes · 10 min read

iQIYI’s unified “Tongtian Tower” big‑data platform integrates analytics, AI and open APIs to turn viewer behavior and public sentiment into market insights, personalized recommendations, smart casting and churn‑prediction tools, embedding a data‑driven culture that fuels its rapid subscriber growth and revenue surge.
AIbig datacontent recommendation
0 likes · 12 min read

Meipai’s personalized recommendation system leverages massive user‑behavior data to build behavior‑driven video clusters—evolving from TopicModel through Item2vec and Keyword Propagation to a DSSM deep model—boosting ranking AUC, enhancing UI diversity, similar‑video search, niche discovery, and feature engineering.
DSSMItem2VecRecommendation System
0 likes · 22 min read

Meituan‑Dianping’s User Action System unifies disparate user‑behavior events with a 5W1H format, ingests them via a proprietary MAPI channel into Kafka, processes them in real‑time using Storm and a Lambda batch‑speed architecture, and delivers millisecond‑level responses for billions of daily events while offering flexible, modular query and storage options.
KafkaLambda architectureStorm
0 likes · 17 min read


21CTODec 17, 2017 · Artificial Intelligence
This article explains the fundamentals of collaborative filtering, detailing explicit and implicit user feedback, power‑law behavior patterns, neighborhood‑based and latent‑factor recommendation algorithms, and how they are applied in e‑commerce and social platforms.
AIcollaborative filteringlatent factor model
0 likes · 8 min read

This article explains user behavior concepts and feedback types, introduces collaborative filtering methods including user‑based, item‑based and latent factor models, discusses similarity measures, power‑law distributions, and practical considerations such as negative sampling, providing a comprehensive overview for building recommendation systems.
collaborative filteringlatent factor modelmachine learning
0 likes · 9 min read

This article describes Qunar's end‑to‑end user behavior data pipeline, covering offline and real‑time ETL processes, system architecture, Dubbo service interfaces, monitoring, optimizations, and the numerous product applications that leverage the unified behavior dataset.
ETLdata pipelinerecommendation systems
0 likes · 15 min read

The article explains how to move beyond macro app metrics by collecting offline and real‑time user data, storing it in HDFS, processing it with Spark, visualizing behavior paths as state‑machine trees, and performing branch‑funnel analysis to uncover conversion bottlenecks and improve product quality.
AnalyticsFunnel Analysisbig data
0 likes · 5 min read

This article explains Ctrip's flight ticket tracking framework (UBT), detailing client‑side and server‑side event collection methods, the purpose and trade‑offs of each tracking type, metric definitions, data association challenges, common pitfalls, and best practices for reliable data‑driven analysis.
AnalyticsCtripMetrics
0 likes · 20 min read

This article describes Qunar's personalized demand prediction system for the "Guess You Like" card, detailing how user‑demand associations are mined via rule engines, collaborative filtering, LBS and manual rules, and how ranking models evolve from subjective Bayes to RankBoost and LambdaMart, with experimental evaluation and future LSTM plans.
AIRankingTravel
0 likes · 10 min read


21CTOMar 18, 2016 · Artificial Intelligence
This article outlines ten practical key points—including leveraging explicit and implicit feedback, hybridizing algorithms, handling temporal and geographic factors, exploiting social ties, solving cold‑start issues, optimizing presentation, defining clear metrics, ensuring real‑time updates, and scaling big‑data processing—to help engineers design effective intelligent recommendation systems.
PersonalizationRecommendation Systemcold start
0 likes · 18 min read


21CTONov 8, 2015 · Frontend Development
The article explains why user‑behavior data is often ignored by UED teams, outlines a three‑stage collection‑analysis‑reporting pipeline, and shows how JavaScript running on V8/Node.js can empower front‑end developers to process massive logs, reducing reliance on separate BI resources.
JavaScriptdata analyticsfrontend
0 likes · 9 min read

Benedict Evans analyses how smartphones turned into social platforms, comparing WeChat's app‑as‑platform strategy with Facebook Messenger's message‑as‑app approach, and explores the structural challenges, user‑behavior dynamics, and potential future evolutions of mobile messaging ecosystems.
Facebook MessengerWeChatapp ecosystems
0 likes · 13 min read
