BestHub
Sign in
Tag

user retention

1 views collected around this technical thread.

Zhihu Tech Column
Zhihu Tech Column
Jun 11, 2025 · Artificial Intelligence

How Minute‑Level Time Decay Boosts User Retention Modeling in Recommendation Systems

This article presents a novel minute‑level future‑reward framework with dual‑delay incentives, activity‑based attribution, multi‑task delayed modeling, and sequential streaming training that dramatically improves user retention prediction accuracy and real‑time performance in large‑scale recommendation platforms.

deep learningmulti‑task modelingreal‑time prediction
0 likes · 17 min read
How Minute‑Level Time Decay Boosts User Retention Modeling in Recommendation Systems
DataFunSummit
DataFunSummit
Jun 26, 2024 · Artificial Intelligence

2026 Roadmap for Recommendation Systems: Challenges, Research Directions, and OneRec Integration

This article outlines the current bottlenecks of conventional recommendation pipelines and proposes a comprehensive 2026 research agenda covering retention improvement, user growth, content ecosystem, multi‑objective Pareto optimization, long‑term value modeling, whole‑site optimization, interactive recommendation, personalized modeling, decision‑theoretic formulation, and the OneRec multi‑source fusion framework.

Artificial IntelligenceRecommendation systemslarge language models
0 likes · 18 min read
2026 Roadmap for Recommendation Systems: Challenges, Research Directions, and OneRec Integration
DataFunTalk
DataFunTalk
Apr 3, 2024 · Artificial Intelligence

Future Directions of Recommendation Systems: Retention, User Growth, Content Ecosystem, Multi‑Objective Optimization, and Large‑Model Fusion

This presentation outlines the current bottlenecks of conventional recommendation pipelines and proposes a 2026 roadmap that includes retention improvement, user‑growth strategies, content‑ecosystem metrics, Pareto‑optimal multi‑objective optimization, long‑term value modeling, site‑wide spatial optimization, interactive recommendation, personalized modeling, and the integration of large‑model fusion through the OneRec framework.

Recommendation systemsinteractive recommendationlarge language models
0 likes · 18 min read
Future Directions of Recommendation Systems: Retention, User Growth, Content Ecosystem, Multi‑Objective Optimization, and Large‑Model Fusion
DataFunTalk
DataFunTalk
Nov 16, 2023 · Product Management

User Operations: Methods for User Analysis, Segmentation, and Aha‑Moment Identification

This article provides a comprehensive guide to user operations, covering the definition of user operation, common user analysis techniques, attribute and behavior analysis, segmentation methods using business logic and clustering algorithms, and the concept of the Aha‑moment or magic number for optimizing retention and value.

Aha momentClusteringproduct management
0 likes · 12 min read
User Operations: Methods for User Analysis, Segmentation, and Aha‑Moment Identification
DataFunTalk
DataFunTalk
Aug 3, 2023 · Game Development

Applying A/B Testing to Drive Growth in Tencent Overseas Games

This article explains how Tencent leverages A/B testing across its overseas games, detailing market differences, experimental methodology, multi‑cloud platform compliance, data architecture, and case studies that illustrate how targeted experiments improve user onboarding, gameplay settings, and email‑based re‑engagement.

A/B testingdata pipelinesexperiment design
0 likes · 12 min read
Applying A/B Testing to Drive Growth in Tencent Overseas Games
DataFunSummit
DataFunSummit
Jul 16, 2023 · Game Development

Applying A/B Testing to Drive Growth in Tencent’s Overseas Games

This article explains how Tencent leverages A/B testing across its overseas games, detailing the current market situation, experimental capabilities, multi‑cloud platform architecture, and case studies that illustrate how data‑driven experiments improve user retention, engagement, and overall business growth.

A/B testingGame developmentcloud computing
0 likes · 12 min read
Applying A/B Testing to Drive Growth in Tencent’s Overseas Games
Kuaishou Tech
Kuaishou Tech
Apr 22, 2023 · Artificial Intelligence

Reinforcement Learning for User Retention (RLUR) in Short Video Recommendation Systems

This paper presents RLUR, a reinforcement‑learning algorithm that models user‑retention optimization as an infinite‑horizon request‑based Markov Decision Process, addressing uncertainty, bias, and delayed reward challenges to directly improve retention, DAU, and engagement in short‑video recommendation platforms.

KuaishouRLURrecommendation system
0 likes · 8 min read
Reinforcement Learning for User Retention (RLUR) in Short Video Recommendation Systems
Kuaishou Tech
Kuaishou Tech
Mar 29, 2023 · Artificial Intelligence

ResAct: A Reinforcement Learning Approach for Long-Term User Retention in Sequential Recommendation

The paper introduces ResAct, a reinforcement‑learning framework that improves long‑term user retention in sequential recommendation by constraining the policy space near the online‑serving policy and employing a conditional variational auto‑encoder, residual actor, and state‑action value network, achieving significant gains over existing methods on a large‑scale short‑video dataset.

Recommendation systemsResActreinforcement learning
0 likes · 9 min read
ResAct: A Reinforcement Learning Approach for Long-Term User Retention in Sequential Recommendation
DataFunTalk
DataFunTalk
Dec 8, 2022 · Product Management

Improving New User Retention in a Video App through A/B Testing: A Case Study

This article presents a detailed case study of how a video app team used two rounds of A/B testing with different swipe‑up guide designs to diagnose retention issues, refine the user onboarding experience, and ultimately achieve significant improvements in new‑user retention and engagement metrics.

A/B testingdata analysisexperiment design
0 likes · 10 min read
Improving New User Retention in a Video App through A/B Testing: A Case Study
ByteDance Data Platform
ByteDance Data Platform
Aug 19, 2022 · Product Management

How ByteDance Boosted New User Retention with Incentives and AB Testing

This article reviews ByteDance's practical growth case where the new video recommendation product “M” used a data‑driven incentive system and extensive AB testing to improve first‑week user retention, outlining the design, implementation steps, and methods for identifying core product functions.

AB testinggrowth hackingincentive design
0 likes · 9 min read
How ByteDance Boosted New User Retention with Incentives and AB Testing
DataFunSummit
DataFunSummit
Oct 31, 2021 · Artificial Intelligence

Exploring Generalized Multi‑Objective Recommendation Algorithms for 58 Community

This article details how 58 Community evolved its recommendation system from single‑objective click‑rate optimization to a multi‑objective framework that boosts value‑content share, improves user retention, and leverages cross‑domain embeddings and online CEM‑based parameter tuning to achieve significant performance gains.

CEMCross-Domainembedding
0 likes · 15 min read
Exploring Generalized Multi‑Objective Recommendation Algorithms for 58 Community
DataFunTalk
DataFunTalk
Oct 4, 2021 · Artificial Intelligence

Exploring Multi-Objective Recommendation Algorithms for 58 Community: Cross-Domain Embedding and Online Optimization

This article details how 58 Community improved content value share, click‑through, and user retention by designing a generalized multi‑objective recommendation algorithm that leverages cross‑domain embeddings, DeepFM‑DIN models, EGES‑inspired pre‑training, and online CEM‑based parameter optimization.

CEMcross-domain embeddingdeep learning
0 likes · 16 min read
Exploring Multi-Objective Recommendation Algorithms for 58 Community: Cross-Domain Embedding and Online Optimization
DataFunTalk
DataFunTalk
Dec 26, 2020 · Product Management

Analysis of Soul’s Social Product Strategy, Community, and Growth Metrics

This article provides a comprehensive analysis of the Soul social app, examining its non‑hormonal positioning, community atmosphere, relationship‑chain metrics, content‑driven engagement, algorithmic matching, and future growth strategies, highlighting how these factors drive user retention and scale.

Algorithmcommunity managementgrowth metrics
0 likes · 13 min read
Analysis of Soul’s Social Product Strategy, Community, and Growth Metrics
Architect
Architect
Jun 30, 2020 · Artificial Intelligence

Analyzing TikTok's US Retention Surge: Algorithmic, Operational, and Marketing Factors

The article examines TikTok's dramatic increase in US user retention by dissecting supply‑side content growth, operational localization, marketing exposure, algorithmic matching, and external influences, and then proposes data‑driven and algorithmic interventions to sustain and amplify the platform's growth.

Growth StrategiesTikTokcontent moderation
0 likes · 17 min read
Analyzing TikTok's US Retention Surge: Algorithmic, Operational, and Marketing Factors
DataFunTalk
DataFunTalk
Jun 24, 2020 · Artificial Intelligence

Analyzing TikTok's US Retention Surge: Algorithmic and Operational Insights

The article examines TikTok's rapid retention growth in the United States by dissecting supply, operation, marketing, matching, and external factors, and then explores how data, algorithms, and product strategies such as risk detection, content boosting, user‑content matching, creator incentives, trend identification, and flow control can be leveraged to sustain and amplify this success.

AlgorithmRecommendation systemsTikTok
0 likes · 15 min read
Analyzing TikTok's US Retention Surge: Algorithmic and Operational Insights
JD Retail Technology
JD Retail Technology
Apr 29, 2020 · Product Management

Data‑Driven Growth: From AARRR to RARRA and the Growth Hacking Methodology

This article explains how modern internet businesses can achieve rapid, cost‑effective expansion by shifting from the classic AARRR acquisition‑focused model to the retention‑centric RARRA framework, detailing the five growth stages, retention analysis, activation tactics, referral incentives, monetization strategies, and a systematic growth‑hacking methodology.

AARRRAcquisitionProduct Metrics
0 likes · 36 min read
Data‑Driven Growth: From AARRR to RARRA and the Growth Hacking Methodology
Xianyu Technology
Xianyu Technology
Feb 27, 2020 · Artificial Intelligence

Data-Driven Simulation for User Activity Retention Prediction

By extracting hour‑level activity logs and training supervised models—including CART, GBDT, and neural networks—on user tags, the team simulated short‑term metrics for new reward campaigns, enabling earlier prediction of next‑day retention and shortening experiment cycles despite delayed T+1 data.

AB testingCARTGBDT
0 likes · 9 min read
Data-Driven Simulation for User Activity Retention Prediction
Python Programming Learning Circle
Python Programming Learning Circle
Oct 16, 2019 · Product Management

What Happened to Xiaohongshu? Inside the Data Behind Its 77‑Day Removal

The article analyzes Xiaohongshu’s 77‑day removal, showing a sharp drop in total active users and DAU, a partial rebound driven by loyal users, the scramble for alternative download sources, opportunistic third‑party sellers, and emerging competitors, while highlighting the product‑management challenges of such a disruption.

Xiaohongshuapp removalmobile app
0 likes · 11 min read
What Happened to Xiaohongshu? Inside the Data Behind Its 77‑Day Removal
Baidu Intelligent Testing
Baidu Intelligent Testing
Apr 14, 2016 · Operations

Choosing and Analyzing Operational Metrics for Product Success

The article explains why operators should start from clear goals rather than events, defines meaningful metrics such as user retention and API call volume, shows how to break down and evaluate these metrics, and offers practical advice on data collection, benchmarking, and continuous improvement.

KPIsdata analysismetrics
0 likes · 6 min read
Choosing and Analyzing Operational Metrics for Product Success
Baidu Intelligent Testing
Baidu Intelligent Testing
Feb 19, 2016 · Product Management

Resource Evaluation Model: Defining Metrics, Data Collection Methods, and Quantification

This article explains how to build a resource evaluation model by defining assessment dimensions, selecting metrics for attracting and retaining users, choosing objective and subjective data collection methods, and quantifying each indicator with thresholds and scoring rules, using an O2O food‑delivery example.

Quantitative ScoringResource Qualitydata collection
0 likes · 7 min read
Resource Evaluation Model: Defining Metrics, Data Collection Methods, and Quantification