BestHub
Sign in
Collection size
100 articles
Page 3 of 5
DataFunTalk
DataFunTalk
Aug 9, 2021 · Artificial Intelligence

Calibration Techniques for User Behavior Prediction in Online Advertising: Background, Algorithm Evolution, and Engineering Practice

This article introduces the concept of calibration in trustworthy machine learning, explains why accurate probability estimates are crucial for online advertising, reviews related research and evaluation metrics, and details the evolution of calibration algorithms such as Smoothed Isotonic Regression, Bayes‑SIR, real‑time optimizations, and post‑click conversion models, concluding with engineering deployment and future directions.

Algorithm OptimizationCalibrationMachine Learning
0 likes · 18 min read
Calibration Techniques for User Behavior Prediction in Online Advertising: Background, Algorithm Evolution, and Engineering Practice
Youku Technology
Youku Technology
Oct 30, 2019 · Artificial Intelligence

Data‑Driven Film Marketing and Real‑Time Box Office Prediction

Feng Xinping explains how Alibaba Pictures leverages extensive online user and cinema data to integrate fragmented promotion channels and deliver real‑time, highly accurate box‑office forecasts—addressing challenges like session anomalies and price variance—achieving roughly 1 % error during the 2019 Spring Festival and paving the way for an intelligent, data‑driven film‑marketing infrastructure.

Box Office PredictionData Analyticsfilm marketing
0 likes · 10 min read
Data‑Driven Film Marketing and Real‑Time Box Office Prediction
DaTaobao Tech
DaTaobao Tech
Mar 22, 2022 · Artificial Intelligence

Online Learning for Real‑Time Ranking in Alibaba's Home‑Decor Channel

The article details Alibaba’s end‑to‑end online‑learning pipeline for real‑time ranking in the Taobao home‑decor channel, covering UT log parsing, full‑feature extraction, ODL sample creation, xDeepCTR model training, and deployment, which yielded up to 7.8% CTR improvement and demonstrates the value of rapid model adaptation.

AlibabaOnline Learningmodel training
0 likes · 15 min read
Online Learning for Real‑Time Ranking in Alibaba's Home‑Decor Channel
Kuaishou Tech
Kuaishou Tech
Dec 17, 2024 · Artificial Intelligence

NeurIPS 2024 Auto‑Bidding in Large‑Scale Auctions: Kuaishou Team Wins Both General and AIGB Tracks

The NeurIPS 2024 Auto‑Bidding competition attracted over 15,000 submissions and 1,500 teams, featuring two tracks—General and AI‑Generated Bidding—where Kuaishou’s commercial algorithm team secured first place in both by leveraging reinforcement‑learning‑based online exploration and a decision‑transformer‑driven generative approach, achieving more than a 5% lift in ad revenue.

AdvertisingGenerative ModelsKuaishou
0 likes · 13 min read
NeurIPS 2024 Auto‑Bidding in Large‑Scale Auctions: Kuaishou Team Wins Both General and AIGB Tracks
Alibaba Cloud Developer
Alibaba Cloud Developer
Dec 25, 2019 · Operations

Boosting Guaranteed Display Ads with Large‑Scale Personalized Allocation and Real‑Time Pacing

This article presents a large‑scale distributed algorithm for guaranteed‑delivery advertising that incorporates user‑level personalization, solves a bipartite matching problem with complex constraints, and introduces a real‑time pacing module to smooth delivery while maximizing platform revenue and advertiser satisfaction.

Advertisingallocationdistributed optimization
0 likes · 22 min read
Boosting Guaranteed Display Ads with Large‑Scale Personalized Allocation and Real‑Time Pacing
JD Cloud Developers
JD Cloud Developers
Mar 24, 2025 · Artificial Intelligence

How Multi-Agent Reinforcement Learning Boosts Ad Computation Allocation

This article presents MaRCA, a multi‑agent reinforcement‑learning framework that allocates computation resources across the full ad‑serving chain, modeling user value, compute cost, and action rewards to maximize ad revenue while keeping system load stable under fluctuating traffic.

AIad optimizationcomputation allocation
0 likes · 16 min read
How Multi-Agent Reinforcement Learning Boosts Ad Computation Allocation
JD Tech Talk
JD Tech Talk
Mar 24, 2025 · Artificial Intelligence

MaRCA: Multi‑Agent Reinforcement Learning Computation Allocation for Full‑Chain Ad Serving

This article presents MaRCA, a multi‑agent reinforcement learning framework that allocates computation resources across the full ad‑serving chain by modeling user value, compute consumption, and action rewards, enabling fine‑grained power‑tilting toward high‑quality traffic and achieving significant business gains under strict latency constraints.

ad servingai-optimizationcomputation allocation
0 likes · 16 min read
MaRCA: Multi‑Agent Reinforcement Learning Computation Allocation for Full‑Chain Ad Serving
JD Tech
JD Tech
Apr 8, 2025 · Artificial Intelligence

MaRCA: Multi‑Agent Reinforcement Learning Computation Allocation for Full‑Chain Advertising Systems

The article presents MaRCA, a multi‑agent reinforcement learning framework that models user value, compute consumption, and action reward to allocate limited computation resources across the entire advertising recommendation pipeline, achieving higher ad revenue while keeping system load stable under fluctuating traffic and diverse request values.

Load-Aware SchedulingResource Optimizationadvertising systems
0 likes · 16 min read
MaRCA: Multi‑Agent Reinforcement Learning Computation Allocation for Full‑Chain Advertising Systems
Architecture Digest
Architecture Digest
Jul 28, 2023 · Operations

2023 Internet Company Work Hours Ranking – A Key Metric for Choosing Employers

The article presents the 2023 Internet Company Work Hours Ranking, explaining how weekly work hours are calculated, highlighting average overtime across major firms such as Pinduoduo and Xiaohongshu, and emphasizing that while companies are optimizing, achieving a truly non‑overtime environment still requires broader policy changes.

2023 dataCompany RankingInternet Industry
0 likes · 3 min read
2023 Internet Company Work Hours Ranking – A Key Metric for Choosing Employers
Alimama Tech
Alimama Tech
Sep 7, 2022 · Artificial Intelligence

Curriculum-Guided Bayesian Reinforcement Learning for ROI-Constrained Real-Time Bidding

The paper presents a Curriculum‑Guided Bayesian Reinforcement Learning (CBRL) framework that models ROI‑constrained real‑time bidding as a partially observable constrained MDP, using hard‑margin indicator rewards and a curriculum of relaxed proxy problems to achieve fast, constraint‑satisfying, Bayes‑optimal policies that outperform existing methods on large‑scale industrial data.

Bayesian RLCurriculum LearningMDP
0 likes · 15 min read
Curriculum-Guided Bayesian Reinforcement Learning for ROI-Constrained Real-Time Bidding
DataFunTalk
DataFunTalk
Sep 4, 2021 · Artificial Intelligence

Real‑time Positive/Negative Feedback Sequence Modeling and Multi‑objective Optimization for Taobao Live Ranking

This article presents a practical study on modeling real‑time positive and negative feedback sequences and applying multi‑objective optimization in the re‑ranking stage of Taobao Live, detailing system architecture, feature engineering, loss design, experimental results, and future research directions.

Taobao Livee-commercefeedback modeling
0 likes · 12 min read
Real‑time Positive/Negative Feedback Sequence Modeling and Multi‑objective Optimization for Taobao Live Ranking
Tencent Advertising Technology
Tencent Advertising Technology
Dec 14, 2022 · Artificial Intelligence

A Unified Guaranteed Impression Allocation Framework for Online Display Advertising

This paper proposes a unified guaranteed impression allocation framework (UGA) that jointly models and optimizes contract and real‑time bidding ads, formulates the problem as a non‑convex QCQP, and demonstrates through offline and online experiments that UGA significantly improves platform and advertiser revenue compared to baseline methods.

AdvertisingQCQPimpression allocation
0 likes · 12 min read
A Unified Guaranteed Impression Allocation Framework for Online Display Advertising
AntTech
AntTech
Sep 9, 2022 · Artificial Intelligence

Ant Security Lab Wins Two Golds and One Silver at KDD Cup 2022 with Advanced Keyword Extraction and Self‑Distillation for Product Search

Ant Security Lab's algorithm engineer Lin Jinzheng secured two gold medals and one silver at the KDD Cup 2022, ranking first globally, by applying innovative keyword‑extraction and self‑distillation techniques to improve product search relevance and interactive risk‑control systems.

AIKDD CupProduct Search
0 likes · 4 min read
Ant Security Lab Wins Two Golds and One Silver at KDD Cup 2022 with Advanced Keyword Extraction and Self‑Distillation for Product Search
Alimama Tech
Alimama Tech
May 29, 2024 · Artificial Intelligence

Alibaba Mama Team Papers Accepted at KDD 2024

Alibaba’s Mama technical team secured four paper acceptances at the prestigious KDD 2024 conference in Barcelona, presenting advances such as a diffusion‑based generative bidding model, truthful combinatorial bandit mechanisms for two‑stage ad auctions, bi‑objective contract allocation for guaranteed delivery advertising, and a fast local‑search algorithm for complex contract constraints.

AIAdvertisingBandit
0 likes · 8 min read
Alibaba Mama Team Papers Accepted at KDD 2024
DataFunTalk
DataFunTalk
Jun 14, 2022 · Information Security

Comprehensive Internet Risk Control: Overview, Precise Traffic Perception, and Full‑Scenario Joint Defense and Control

This presentation explores internet risk control, detailing its classification, precise traffic perception methods, and full‑scenario joint defense and control strategies, using Bilibili as a case study to illustrate challenges, adversaries, detection techniques, and mitigation measures.

BilibiliInternet SecurityTraffic analysis
0 likes · 17 min read
Comprehensive Internet Risk Control: Overview, Precise Traffic Perception, and Full‑Scenario Joint Defense and Control
AntTech
AntTech
Jul 21, 2019 · Artificial Intelligence

Alipay’s SIGIR 2019 Papers: Reinforcement Learning for User Intent Prediction and Unsupervised QUEST for Complex Question Answering

At SIGIR 2019 in Paris, Alipay presented two AI research papers—one applying reinforcement learning to predict user intent in customer‑service bots and another introducing the unsupervised QUEST method that builds noisy quasi‑knowledge graphs for answering complex multi‑document questions.

AIKnowledge GraphUnsupervised Learning
0 likes · 5 min read
Alipay’s SIGIR 2019 Papers: Reinforcement Learning for User Intent Prediction and Unsupervised QUEST for Complex Question Answering
Alimama Tech
Alimama Tech
May 23, 2022 · Artificial Intelligence

Alibaba Mama Team Papers Accepted at KDD 2022 and Other Top Conferences

The Alibaba Mama technical team secured five paper acceptances at the prestigious KDD 2022 conference, presenting advances such as curriculum‑guided Bayesian reinforcement learning for ROI‑constrained bidding, adversarial‑gradient driven exploration for click‑through‑rate prediction, externality‑aware transformers for e‑commerce ads, multi‑modal multi‑query pretraining, and generative‑replay streaming graph neural networks.

Advertising BiddingE-commerce SearchKDD 2022
0 likes · 10 min read
Alibaba Mama Team Papers Accepted at KDD 2022 and Other Top Conferences
Model Perspective
Model Perspective
Jan 30, 2026 · Fundamentals

Explore the Six 2026 MCM/ICM Modeling Challenges and How to Tackle Them

The 2026 MCM/ICM competition presents six diverse real‑world problems—from smartphone battery discharge to space‑elevator logistics, dance‑show voting, sports team management, passive solar shading, and generative AI impacts—each requiring continuous‑time or data‑driven mathematical models, sensitivity analysis, and actionable recommendations.

ICMMCMbattery modeling
0 likes · 15 min read
Explore the Six 2026 MCM/ICM Modeling Challenges and How to Tackle Them
Alimama Tech
Alimama Tech
Sep 15, 2021 · Artificial Intelligence

Combining Knowledge Distillation, Exposure Forecasting, and Pacing to Guarantee Brand Exposure on Alibaba's Advertising Platform

Alibaba's advertising platform combines knowledge distillation to score traffic, exposure forecasting via GBDT, and PID-based pacing to guarantee contracted impression volumes while improving CTR/CVR, handling delayed exposure and traffic selection, achieving near‑perfect delivery in large promotions.

AlibabaKnowledge Distillationexposure forecasting
0 likes · 17 min read
Combining Knowledge Distillation, Exposure Forecasting, and Pacing to Guarantee Brand Exposure on Alibaba's Advertising Platform