Tagged articles
user behavior modeling
18 articles · Page 1 of 1
This article reviews a decade of recommendation‑system research, outlines the shift from traditional listwise methods to deep‑learning models, discusses the impact of large language models and AI agents, and presents future directions such as multimodal interaction, responsible AI, cognitive modeling, and ecosystem integration.
recommendation systemsuser behavior modeling
0 likes · 31 min read

The paper presents a comprehensive multi‑scenario recommendation study introducing three models—SACN, SAINet, and DSWIN—that integrate scene‑aware attention, attribute‑level preferences, and contrastive disentanglement to capture distinct user interests, achieving consistent AUC gains and online CTR improvements across real‑world datasets.
CTR predictionContrastive Learningdeep learning
0 likes · 43 min read


NewBeeNLPMay 9, 2024 · Artificial Intelligence
This article summarizes the UniSAR framework, which models four types of fine‑grained user transitions between search and recommendation, demonstrates its effectiveness on public datasets, and shows how joint learning improves both search relevance and recommendation quality.
TransformerUniSARcross-attention
0 likes · 4 min read


NewBeeNLPFeb 4, 2024 · Artificial Intelligence
This article analyzes the original MIND recommendation model, identifies its limitations in capsule design and routing, proposes three practical improvements—including max‑min and Markov‑based capsule initialization and a sparse routing scheme—and validates the gains with offline experiments and real‑world business metrics.
AIMINDcapsule network
0 likes · 20 min read


AntTechNov 7, 2023 · Artificial Intelligence
The paper proposes a multi‑scale stochastic distribution prediction (MSDP) framework that learns robust user behavior representations by predicting behavior distributions over random time windows, incorporates contrastive regularization, and demonstrates superior performance on both proprietary financial risk data and a public e‑commerce dataset compared with existing masked and next‑behavior pre‑training methods.
AIMulti-ScalePretraining
0 likes · 13 min read

This paper presents TWIN, a two-stage interest network that aligns the similarity metrics of coarse‑grained and fine‑grained modules to improve lifelong user behavior modeling for CTR prediction in large‑scale online recommendation systems.
Attention MechanismCTR predictionKuaishou
0 likes · 10 min read

This article presents Fliggy's work on user travel demand prediction, outlining the unique challenges of travel scenarios, the evolution of recall and ranking algorithms—including multi‑task learning, graph‑based models, and intention‑capture mechanisms—and discusses future research directions such as long‑sequence modeling and cross‑domain learning.
Graph Neural Networksmachine learningmulti-task learning
0 likes · 19 min read

The Dewu app’s new multi‑objective ranking model replaces the shallow ESMM baseline with a DeepFM‑based MLP and a Deep Interest Transformer that encodes up to 120 recent user actions, adds a dedicated bias network, and fuses short‑ and long‑term interests, achieving modest CTR and CVR AUC improvements while planning future tab‑specific extensions.
CTRCVRRecommendation System
0 likes · 13 min read

The article presents JD's e‑commerce recommendation system, detailing its four‑stage ranking pipeline, multi‑objective optimization with personalized fusion, transformer‑based user behavior sequence modeling, fine‑grained behavior modeling, and multimodal feature integration, and shares experimental results and engineering optimizations.
Multi-Objective Optimizatione-commercemultimodal features
0 likes · 17 min read

The article presents JD's end‑to‑end recommendation pipeline, detailing the four‑stage ranking chain, challenges of fine‑ranking, and practical solutions including multi‑objective learning, transformer‑based user behavior sequence modeling, fine‑grained click behavior integration, and multimodal image features, with offline and online performance gains.
Multi-Objective Optimizationfine-grained behaviormultimodal features
0 likes · 18 min read

User behavior sequence modeling, crucial for search and recommendation advertising ranking, has evolved from simple pooling to attention, RNN, capsule, and Transformer architectures, with industrial applications across e‑commerce, social, video, and music platforms, and future directions include time‑aware, multi‑dimensional, and self‑supervised approaches.
AttentionSequence ModelingTransformer
0 likes · 24 min read

This article presents a comprehensive technical overview of Momo's model‑based recall system for social recommendation, detailing the underlying user‑scenario behavior models, social graph embeddings, multimodal content semantics, and deployment results that improve matching relevance and user interaction rates.
EmbeddingGraph Neural NetworkMomo
0 likes · 19 min read

This article presents the Search‑Based Interest Model (SIM), a two‑stage retrieval framework that indexes a user's entire behavior history to enable long‑term interest modeling for click‑through‑rate prediction, demonstrating practical deployment and improved recommendation of long‑term interests in e‑commerce.
AICTR predictionLong-Term Interest
0 likes · 16 min read

The article presents a comprehensive overview of NetEase Cloud Music's recommendation system, detailing its rapid user growth, diverse music‑recommendation scenarios, differences from e‑commerce recommendation, and the evolution of recall and ranking models that leverage real‑time interest vectors, dynamic multi‑interest modeling, knowledge graphs, long‑short‑term interest mining, and multi‑path fusion to deliver personalized music experiences.
AI Algorithmsinterest evolutionknowledge graph
0 likes · 20 min read

This article introduces a Kalman Filtering Attention (KFAtt) framework that enhances click‑through‑rate (CTR) prediction by modeling user behavior with a Kalman‑filter‑based attention mechanism and a frequency‑capped variant, addressing new‑interest coverage and frequency bias in e‑commerce scenarios.
Attention MechanismCTR predictionKalman filter
0 likes · 11 min read

The paper presents an optimized CTR prediction model for Tencent’s App Store that merges multi‑behavior shared embeddings, long‑term DeepWalk graph embeddings, BERT‑derived app description vectors, and attention‑based fusion, reducing parameters while improving bias, AUC, and recommendation performance for sparse, long‑tail data.
BERTCTR predictionDeepWalk
0 likes · 9 min read

The article introduces EdgeRec, an edge‑computing powered recommendation framework that moves user‑interest perception and ranking to the client side to overcome latency in traditional cloud‑centric recommender systems, detailing its architecture, heterogeneous behavior modeling, attention‑based reranking, and experimental gains.
Edge ComputingRankingdeep learning
0 likes · 13 min read

This article presents a co-designed algorithm‑system solution—MIMN and an independent UIC module—that enables ultra‑long user behavior modeling for click‑through rate prediction, delivering significant offline AUC gains and online CTR/RPM improvements in Alibaba's display advertising platform.
CTR predictiondeep learningmemory networks
0 likes · 12 min read
