Tagged articles
User Modeling
42 articles · Page 1 of 1
Himalaya uses LLMs as user preference proxies to automatically optimize recommendation parameters across recall, ranking, and re-ranking stages, leveraging user context and long-term memory to generate personalized parameters via a parameter center, achieving significant metric gains for low-frequency users.
HimalayaLLMPBox
0 likes · 26 min read

The article explains how Honcho transforms scattered conversation facts into a structured user model through a dialectic reasoning loop, detailing memory vs. user model differences, tool architecture, recall modes, prefetch caching, cost‑control mechanisms, peer cards, and common pitfalls for building ever‑more personalized AI agents.
AgentDialectic ReasoningHoncho
0 likes · 15 min read

LifeSim introduces a long‑horizon user life simulation framework that jointly models user cognition via a BDI engine and external environment, enabling realistic evaluation of personalized LLM assistants through the LifeSim‑Eval benchmark, which reveals current models excel at explicit intents but struggle with hidden intents and long‑term user understanding.
BDI modelLLM EvaluationLifeSim
0 likes · 9 min read

Alibaba’s 1688 platform leverages inference‑based large language models to enhance recommendation discovery, addressing the filter‑bubble problem by analyzing long‑term buyer behavior, compressing extensive activity streams, generating nuanced demand queries, and integrating multimodal data and market trend agents to deliver more diverse, explainable product suggestions for B‑type buyers.
AIE‑commerceUser Modeling
0 likes · 23 min read

The article explains why using the vague term “user” in software design creates hidden security flaws, illustrates the problem with examples from ticket booking, Unix, and SaaS systems, and urges early terminology planning to avoid costly redesigns.
User Modelingaccess controlsoftware design
0 likes · 9 min read

This article reviews Professor Jin Yucheng’s research on conversational recommender systems, detailing a human‑centric evaluation framework, the CRS‑Que assessment model, and ChatGPT‑based experiments that reveal how dialogue quality, user trust, and prompt design jointly shape system performance.
AIUser Modelingconversational recommender systems
0 likes · 16 min read

This article details Meituan Waimai's feed advertising system, covering business characteristics, the evolution of estimation models, and practical implementations such as decision‑path modeling, ultra‑long/wide user modeling, full‑reconstruction techniques, and the integration of large language models for CTR prediction.
CTR estimationLLMMeituan
0 likes · 22 min read


NewBeeNLPJul 22, 2024 · Artificial Intelligence
This article examines Meta's SUM (Scaling User Modeling) system, detailing its upstream‑downstream architecture, the SOAP online asynchronous serving platform, production optimizations, and extensive offline and online experiments that demonstrate significant gains in ad personalization performance.
MetaPersonalizationUser Modeling
0 likes · 19 min read

At CNCC 2023, leading researchers and industry experts convened to examine how large language models can transform recommendation systems, outlining four core challenges—model integration, fluency versus intelligence, hallucination versus deception, and user understanding—while highlighting opportunities such as multimodal content, cold‑start solutions, zero‑shot ranking, instruction‑driven algorithms, and responsible, interactive recommendation pipelines.
AICNCC 2023LLM Applications
0 likes · 16 min read

This article provides a detailed overview of modern recommendation system technology, covering system architecture, user understanding layers, various recall and ranking techniques, additional algorithmic directions such as cold‑start and bias modeling, and the evolving evaluation metrics used in practice.
RecallUser Modelingbias modeling
0 likes · 14 min read

This article presents a detailed survey of recent advances in recommendation system technology, covering system architecture, user understanding layers, various recall methods, ranking techniques, auxiliary algorithms such as cold-start and bias modeling, and evaluation metrics, with references to industry practices and academic research.
AIEvaluation MetricsUser Modeling
0 likes · 13 min read

The paper presents an intelligent reach system for e‑commerce that automatically selects audience, timing, channel, welfare and creative content using user, content and decision models—including XGBoost churn predictions, NLP‑generated copy, Bayesian CTR estimation and linear‑programming optimization—resulting in a 17.4 % rise in paying users and a 5 % revenue boost over manual methods.
Decision OptimizationIntelligent ReachUser Modeling
0 likes · 20 min read

This article presents the design and implementation of the Real‑Time User Understanding Service (RTUS) for the Fliggy travel platform, detailing its architecture, multi‑chain data fusion, model and data reuse techniques, and several AI‑driven algorithms for cold‑start interest representation, intent prediction, and destination forecasting, together with extensive offline and online experimental results.
AIIntent PredictionTravel Industry
0 likes · 21 min read

This article summarizes four CIKM 2022 papers that present a client‑side short‑video recommender, the fully‑observed KuaiRec dataset, the unbiased KuaiRand sequential recommendation dataset, and an industrial‑scale solution for billion‑user lifetime value prediction, highlighting their motivations, methods, and reported impacts.
User Modelingdatasetsshort video
0 likes · 8 min read

Disney’s Content Discovery team introduces M5, a multi‑modal, multi‑interest, multi‑scenario recall model that enhances VOD and live streaming recommendations by leveraging rich metadata, user behavior, and contextual features, outperforming baseline methods with significant hit‑ratio gains across Hulu and Disney+.
M5 modelMulti-modalUser Modeling
0 likes · 22 min read

Cold‑Transformer tackles the user cold‑start problem by introducing an Embedding Adaption layer that refines sparse user embeddings using context‑aware fused behavior sequences and a label‑encoding scheme, preserving a dual‑tower design and achieving state‑of‑the‑art performance on public and industrial datasets.
User Modelingcold-startembedding adaptation
0 likes · 21 min read

This article presents a comprehensive overview of how contrastive learning can alleviate data sparsity and distribution bias in recommendation systems, detailing its theoretical advantages, recent research progress in computer vision and NLP, and a multi‑task self‑supervised framework applied to Kuaishou's short‑video ranking pipeline with significant offline and online performance gains.
AIContrastive LearningKuaishou
0 likes · 21 min read

This presentation details how JD applied reinforcement learning—using RNN‑based user state modeling and a DDPG framework—to improve e‑commerce search ranking by optimizing long‑term cumulative value, showing significant offline and online gains in conversion and GMV.
DDPGRNNUser Modeling
0 likes · 20 min read

The paper tackles Taobao Live’s cold‑start problem for new users by introducing a multi‑channel lifelong product‑sequence network that enriches purchase histories with side information, extracts relevance‑focused subsequences across five channels, and integrates them via target‑attention DIN, achieving substantial offline and online performance gains, especially for low‑activity users.
User Modelingcold starte-commerce
0 likes · 23 min read

This article presents a comprehensive overview of NetEase Cloud Music's advertising system, detailing its architecture, core challenges, CTR and CVR prediction models, feature engineering, model evolution from LR to deep learning, user vector modeling, and practical recommendations for improving ad performance.
AdvertisingCTR predictionNetEase Cloud Music
0 likes · 15 min read

CONDE, a concept‑aware denoising graph neural network proposed by Wuhan University and Kuaishou, leverages heterogeneous three‑part graphs, attention‑based graph convolutions, and Gumbel‑Softmax‑driven edge sampling to filter noisy user‑video interactions, achieving up to 6 % AUC improvement on short‑video and e‑commerce recommendation tasks.
AIDenoisingGraph Neural Network
0 likes · 10 min read


21CTOSep 7, 2021 · Artificial Intelligence
This article examines the rapid growth of short‑video platforms, outlines the core problems a recommendation system must solve for users, creators, and advertisers, describes the end‑to‑end pipeline, explores multi‑objective modeling and fusion techniques, and discusses long‑term value estimation for sustained user engagement.
AIRecommendation SystemUser Modeling
0 likes · 8 min read

This article presents Alibaba Fliggy's personalized marketing platform for travel, detailing its multi‑scene architecture, user‑session modeling, graph‑based recommendation algorithms, cold‑start strategies, cross‑domain user mapping, and a hierarchical travel‑play tag system that together enable large‑scale, real‑time, thousand‑person‑one‑face marketing.
Graph Neural NetworkPersonalized RecommendationTravel
0 likes · 20 min read

This article examines Toutiao’s rapid growth from a small startup to a platform serving over 500 million users, detailing its data collection, user modeling, cold‑start handling, recommendation engines, storage solutions, messaging push system, micro‑service design, and virtualized PaaS infrastructure that enable high‑throughput, personalized news delivery.
User Modelingcloud computingdata pipeline
0 likes · 9 min read

This article provides a comprehensive overview of Toutiao's rapid growth, massive user base, data collection pipelines, user modeling, recommendation engine, storage solutions, message push strategies, micro‑service architecture, and virtualization PaaS platform, illustrating how big‑data technologies enable personalized news delivery at scale.
Recommendation SystemToutiaoUser Modeling
0 likes · 8 min read

This talk explains how Quanmin K Song extracts high‑quality user‑generated content, designs multi‑stage recall pipelines—including attribute‑based, model‑based, and other recall methods—and applies iterative model improvements, negative‑sampling strategies, and bias‑mitigation techniques to enhance recommendation performance.
Content MiningRecall ModelUser Modeling
0 likes · 12 min read

The article explains how the vague term “user” creates design flaws and security vulnerabilities across domains such as airline booking systems, Unix environments, and SaaS platforms, and argues for precise terminology to avoid costly rework and confused‑deputy attacks.
SecurityTerminologyUser Modeling
0 likes · 7 min read

Peng Mo’s talk details Tencent Kankan’s billion‑user feed architecture—layered data, recall, ranking, and exposure control—while addressing real‑time feature generation, massive concurrency, memory‑intensive caching, and fast indexing, and explains solutions such as multi‑level caches, online minute‑level model updates, Redis bloom‑filter exposure filtering, a lock‑free hash‑plus‑linked‑list index, and distributed optimizations that halve latency to under 500 ms and support auto‑scaling and cold‑start handling.
Recommendation SystemUser Modelinglarge-scale architecture
0 likes · 15 min read

This article presents Alibaba's comprehensive approach to user modeling for search CTR/CVR ranking, detailing the abstraction of user information, multi‑scale behavior processing, enhanced transformer‑based model structures, client‑side click and exposure modeling, and experimental results showing significant AUC improvements.
AlibabaAttention MechanismCTR prediction
0 likes · 18 min read

This article presents Alibaba Fliggy's personalized marketing platform for travel, detailing its architecture, scenario and functional abstractions, user‑modeling pipelines, full‑stack traffic control, cold‑start techniques, cross‑domain mapping, heterogeneous graph modeling, and a hierarchical travel‑play tag system to achieve thousand‑person‑one‑face recommendation across daily and promotional scenes.
Graph Neural NetworkPersonalized RecommendationTravel
0 likes · 22 min read

The article explains how the vague term “user” leads to design flaws and security vulnerabilities across systems like ticket‑booking platforms, Unix, and SaaS, and argues that precise terminology and early conceptual planning can prevent costly rework.
Best PracticesUser Modelingaccess control
0 likes · 8 min read

This article details the technical architecture behind WeChat's "Look" content recall, covering content sourcing, profiling, multimodal tagging, knowledge‑graph representations, propensity and target detection, multi‑stage recall pipelines, and a range of deep learning models including sequence, translation, BERT, dual‑tower, hybrid, and graph neural network approaches.
Graph Neural NetworkUser ModelingWeChat AI
0 likes · 32 min read

This article details Alibaba’s Taobao search CTR/CVR user modeling approach, covering background, model architecture with self‑attention and attention pooling, handling short‑term, long‑term, and on‑device behavior sequences, experimental results showing AUC improvements, and future directions.
CTR predictionSelf-AttentionUser Modeling
0 likes · 20 min read


21CTOOct 6, 2019 · Artificial Intelligence
This article explains the architecture and principles of Toutiao’s recommendation system, covering its three‑dimensional model of content, user and environment features, content analysis techniques, user tagging, real‑time training pipelines, evaluation methods, and content safety measures that together drive personalized feeds.
Content AnalysisReal-time TrainingRecommendation System
0 likes · 18 min read

This article reviews recent advances in applying reinforcement learning to recommendation systems, explains the fundamental RL concepts, discusses the specific challenges such as large action spaces, bias, and long‑term reward modeling, and summarizes two influential YouTube papers along with practical insights and future directions.
Off-PolicyUser Modelinglong-term reward
0 likes · 13 min read


AntTechJun 10, 2019 · Artificial Intelligence
This article presents a model‑based reinforcement learning framework for recommendation systems that uses a generative adversarial user model to simultaneously learn user behavior dynamics and reward functions, enabling efficient Cascading‑DQN policy learning and achieving superior long‑term user rewards and click‑through rates in experiments.
Cascading DQNGenerative Adversarial NetworksUser Modeling
0 likes · 9 min read

This article explains how MaFengWo builds a three‑dimensional user content contribution model—combining activity, popularity, and sharing willingness—to objectively score UGC creators, improve recommendation strategies, and drive more effective travel‑related services.
RFM modelUGC analysisUser Modeling
0 likes · 12 min read


21CTOMay 31, 2019 · Information Security
The article explains how the vague term “User” leads to poor requirements, hidden security flaws like the Confused Deputy problem, and costly redesigns, urging developers to adopt precise terminology such as “team” and “member” early in a project.
TerminologyUser Modelingaccess control
0 likes · 8 min read

This article explains how personalized recommendation systems work in e‑commerce platforms like Taobao, covering the fundamentals of machine learning, feature engineering, model building, evaluation, and the business motivations behind delivering unique, user‑specific product suggestions.
AIPersonalized RecommendationUser Modeling
0 likes · 22 min read

This paper proposes a novel attention‑based framework that groups and encodes heterogeneous user behavior sequences into separate semantic subspaces, applies self‑attention to capture inter‑behavior influences, and demonstrates faster training and comparable or improved recommendation performance across multiple tasks and datasets.
Self-AttentionUser Modelingheterogeneous behavior
0 likes · 12 min read


21CTOAug 6, 2016 · Artificial Intelligence
This article outlines Toutiao's rapid growth, its data pipelines, user modeling, recommendation system, storage solutions, and push notification strategies that together enable personalized news delivery to hundreds of millions of users.
AIPersonalizationRecommendation System
0 likes · 7 min read


21CTOJan 3, 2016 · Artificial Intelligence
This article explores how Meilishuo, China’s leading fast‑fashion discovery platform, tackles fragmented mobile attention by using AI‑powered personalization techniques—including user modeling, real‑time feedback, and tailored push notifications—to deliver highly relevant fashion recommendations and boost user engagement.
AIPersonalizationRecommendation System
0 likes · 6 min read
