Awesome
计算广告论文、学习资料、业界分享
动态更新工作中实现或者阅读过的计算广告相关论文、学习资料和业界分享，作为自己工作的总结，也希望能为计算广告相关行业的同学带来便利。 所有资料均来自于互联网，如有侵权，请联系王喆。同时欢迎对计算广告感兴趣的同学与我讨论相关问题，我的联系方式如下：
- Email: wzhe06@gmail.com
- LinkedIn: 王喆的LinkedIn
- 知乎私信: 王喆的知乎
会不断加入一些重要的计算广告相关论文和资料，并去掉一些过时的或者跟计算广告不太相关的论文
New![Airbnb Embedding] Real-time Personalization using Embeddings for Search Ranking at Airbnb (Airbnb 2018) <br /> 2018 KDD best paper, Airbnb基于embeddding构建的实时搜索推荐系统New![DIEN] Deep Interest Evolution Network for Click-Through Rate Prediction (Alibaba 2019) <br /> 阿里提出的深度兴趣网络（Deep Interest Network）最新改进DIEN
其他相关资源
- 张伟楠的RTB Papers列表<br />
- 基于Spark MLlib的CTR预估模型(LR, FM, RF, GBDT, NN, PNN) <br />
- 推荐系统相关论文和资源列表 <br />
- Honglei Zhang的推荐系统论文列表
目录
Optimization Method
Online Optimization，Parallel SGD，FTRL等优化方法，实用并且能够给出直观解释的文章
- Google Vizier A Service for Black-Box Optimization <br />
- 在线最优化求解(Online Optimization)-冯扬 <br />
- Hogwild A Lock-Free Approach to Parallelizing Stochastic Gradient Descent <br />
- Parallelized Stochastic Gradient Descent <br />
- A Survey on Algorithms of the Regularized Convex Optimization Problem <br />
- Follow-the-Regularized-Leader and Mirror Descent- Equivalence Theorems and L1 Regularization <br />
- A Review of Bayesian Optimization <br />
- Taking the Human Out of the Loop- A Review of Bayesian Optimization <br />
- 非线性规划 <br />
Topic Model
话题模型相关文章，PLSA，LDA，进行广告Context特征提取，创意优化经常会用到Topic Model
- 概率语言模型及其变形系列 <br />
- Parameter estimation for text analysis <br />
- LDA数学八卦 <br />
- Distributed Representations of Words and Phrases and their Compositionality <br />
- Dirichlet Distribution, Dirichlet Process and Dirichlet Process Mixture(PPT) <br />
- 理解共轭先验 <br />
Google Three Papers
Google三大篇，HDFS，MapReduce，BigTable，奠定大数据基础架构的三篇文章，任何从事大数据行业的工程师都应该了解
- MapReduce Simplified Data Processing on Large Clusters <br />
- The Google File System <br />
- Bigtable A Distributed Storage System for Structured Data <br />
Factorization Machines
FM因子分解机模型的相关paper，在计算广告领域非常实用的模型
- FM PPT by CMU <br />
- Factorization Machines Rendle2010 <br />
- libfm-1.42.manual <br />
- Scaling Factorization Machines to Relational Data <br />
- fastFM- A Library for Factorization Machines <br />
Embedding
- [Negative Sampling] Word2vec Explained Negative-Sampling Word-Embedding Method (2014) <br />
- [SDNE] Structural Deep Network Embedding (THU 2016) <br />
- [Item2Vec] Item2Vec-Neural Item Embedding for Collaborative Filtering (Microsoft 2016) <br />
- [Word2Vec] Distributed Representations of Words and Phrases and their Compositionality (Google 2013) <br />
- [Word2Vec] Word2vec Parameter Learning Explained (UMich 2016) <br />
- [Node2vec] Node2vec - Scalable Feature Learning for Networks (Stanford 2016) <br />
- [Graph Embedding] DeepWalk- Online Learning of Social Representations (SBU 2014) <br />
- [Airbnb Embedding] Real-time Personalization using Embeddings for Search Ranking at Airbnb (Airbnb 2018) <br />
- [Alibaba Embedding] Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba (Alibaba 2018) <br />
- [Word2Vec] Efficient Estimation of Word Representations in Vector Space (Google 2013) <br />
- [LINE] LINE - Large-scale Information Network Embedding (MSRA 2015) <br />
Budget Control
广告系统中Pacing，预算控制，以及怎么把预算控制与其他模块相结合的问题
- Budget Pacing for Targeted Online Advertisements at LinkedIn <br />
- 广告系统中的智能预算控制策略 <br />
- Predicting Traffic of Online Advertising in Real-time Bidding Systems from Perspective of Demand-Side Platforms <br />
- Real Time Bid Optimization with Smooth Budget Delivery in Online Advertising <br />
- PID控制经典培训教程 <br />
- PID控制原理与控制算法 <br />
- Smart Pacing for Effective Online Ad Campaign Optimization <br />
Tree Model
树模型和基于树模型的boosting模型，树模型的效果在大部分问题上非常好，在CTR，CVR预估及特征工程方面的应用非常广
- Introduction to Boosted Trees <br />
- Classification and Regression Trees <br />
- Greedy Function Approximation A Gradient Boosting Machine <br />
- Classification and Regression Trees <br />
Guaranteed Contracts Ads
事实上，现在很多大的媒体主仍是合约广告系统，合约广告系统的在线分配，Yield Optimization，以及定价问题都是非常重要且有挑战性的问题
- A Dynamic Pricing Model for Unifying Programmatic Guarantee and Real-Time Bidding in Display Advertising <br />
- Pricing Guaranteed Contracts in Online Display Advertising <br />
- Risk-Aware Dynamic Reserve Prices of Programmatic Guarantee in Display Advertising <br />
- Pricing Guidance in Ad Sale Negotiations The PrintAds Example <br />
- Risk-Aware Revenue Maximization in Display Advertising <br />
Classic CTR Prediction
- [LR] Predicting Clicks - Estimating the Click-Through Rate for New Ads (Microsoft 2007) <br />
- [FFM] Field-aware Factorization Machines for CTR Prediction (Criteo 2016) <br />
- [GBDT+LR] Practical Lessons from Predicting Clicks on Ads at Facebook (Facebook 2014) <br />
- [PS-PLM] Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction (Alibaba 2017) <br />
- [FTRL] Ad Click Prediction a View from the Trenches (Google 2013) <br />
- [FM] Fast Context-aware Recommendations with Factorization Machines (UKON 2011) <br />
Bidding Strategy
计算广告中广告定价，RTB过程中广告出价策略的相关问题
- Research Frontier of Real-Time Bidding based Display Advertising <br />
- Budget Constrained Bidding by Model-free Reinforcement Learning in Display Advertising <br />
- Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising <br />
- Real-Time Bidding by Reinforcement Learning in Display Advertising <br />
- Combining Powers of Two Predictors in Optimizing Real-Time Bidding Strategy under Constrained Budget <br />
- Bid-aware Gradient Descent for Unbiased Learning with Censored Data in Display Advertising <br />
- Optimized Cost per Click in Taobao Display Advertising <br />
- Real-Time Bidding Algorithms for Performance-Based Display Ad Allocation <br />
- Deep Reinforcement Learning for Sponsored Search Real-time Bidding <br />
Computational Advertising Architect
广告系统的架构问题
- [TensorFlow Whitepaper]TensorFlow- Large-Scale Machine Learning on Heterogeneous Distributed Systems <br />
- 大数据下的广告排序技术及实践 <br />
- 美团机器学习 吃喝玩乐中的算法问题 <br />
- [Parameter Server]Scaling Distributed Machine Learning with the Parameter Server <br />
- Display Advertising with Real-Time Bidding (RTB) and Behavioural Targeting <br />
- A Comparison of Distributed Machine Learning Platforms <br />
- Efficient Query Evaluation using a Two-Level Retrieval Process <br />
- [TensorFlow Whitepaper]TensorFlow- A System for Large-Scale Machine Learning <br />
- [Parameter Server]Parameter Server for Distributed Machine Learning <br />
- Overlapping Experiment Infrastructure More, Better, Faster Experimentation <br />
Machine Learning Tutorial
机器学习方面一些非常实用的学习资料
- 各种回归的概念学习 <br />
- 机器学习总图 <br />
- Efficient Estimation of Word Representations in Vector Space <br />
- Rules of Machine Learning- Best Practices for ML Engineering <br />
- An introduction to ROC analysis <br />
- Deep Learning Tutorial <br />
- 广义线性模型 <br />
- 贝叶斯统计学(PPT) <br />
- 关联规则基本算法及其应用 <br />
Transfer Learning
迁移学习相关文章，计算广告中经常遇到新广告冷启动的问题，利用迁移学习能较好解决该问题
- [Multi-Task]An Overview of Multi-Task Learning in Deep Neural Networks <br />
- Scalable Hands-Free Transfer Learning for Online Advertising <br />
- A Survey on Transfer Learning <br />
Deep Learning CTR Prediction
- [DCN] Deep & Cross Network for Ad Click Predictions (Stanford 2017) <br />
- [Deep Crossing] Deep Crossing - Web-Scale Modeling without Manually Crafted Combinatorial Features (Microsoft 2016) <br />
- [PNN] Product-based Neural Networks for User Response Prediction (SJTU 2016) <br />
- [DIN] Deep Interest Network for Click-Through Rate Prediction (Alibaba 2018) <br />
- [ESMM] Entire Space Multi-Task Model - An Effective Approach for Estimating Post-Click Conversion Rate (Alibaba 2018) <br />
- [Wide & Deep] Wide & Deep Learning for Recommender Systems (Google 2016) <br />
- [xDeepFM] xDeepFM - Combining Explicit and Implicit Feature Interactions for Recommender Systems (USTC 2018) <br />
- [Image CTR] Image Matters - Visually modeling user behaviors using Advanced Model Server (Alibaba 2018) <br />
- [AFM] Attentional Factorization Machines - Learning the Weight of Feature Interactions via Attention Networks (ZJU 2017) <br />
- [DIEN] Deep Interest Evolution Network for Click-Through Rate Prediction (Alibaba 2019) <br />
- [DSSM] Learning Deep Structured Semantic Models for Web Search using Clickthrough Data (UIUC 2013) <br />
- [FNN] Deep Learning over Multi-field Categorical Data (UCL 2016) <br />
- [DeepFM] A Factorization-Machine based Neural Network for CTR Prediction (HIT-Huawei 2017) <br />
- [NFM] Neural Factorization Machines for Sparse Predictive Analytics (NUS 2017) <br />
Exploration and Exploitation
探索和利用，计算广告中非常经典，也是容易被大家忽视的问题，其实所有的广告系统都面临如何解决新广告主冷启动，以及在效果不好的情况下如何探索新的优质流量的问题，希望该目录下的几篇文章能够帮助到你
- An Empirical Evaluation of Thompson Sampling <br />
- Dynamic Online Pricing with Incomplete Information Using Multi-Armed Bandit Experiments <br />
- 广告系统中的探索与利用算法 <br />
- Finite-time Analysis of the Multiarmed Bandit Problem <br />
- A Fast and Simple Algorithm for Contextual Bandits <br />
- Customer Acquisition via Display Advertising Using MultiArmed Bandit Experiments <br />
- Mastering the game of Go with deep neural networks and tree search <br />
- Exploring compact reinforcement-learning representations with linear regression <br />
- Incentivizting Exploration in Reinforcement Learning with Deep Predictive Models <br />
- Bandit Algorithms Continued- UCB1 <br />
- A Contextual-Bandit Approach to Personalized News Article Recommendation(LinUCB) <br />
- Exploitation and Exploration in a Performance based Contextual Advertising System <br />
- Bandit based Monte-Carlo Planning <br />
- Random Forest for the Contextual Bandit Problem <br />
- Unifying Count-Based Exploration and Intrinsic Motivation <br />
- Analysis of Thompson Sampling for the Multi-armed Bandit Problem <br />
- Thompson Sampling PPT <br />
- Hierarchical Deep Reinforcement Learning- Integrating Temporal Abstraction and Intrinsic Motivation <br />
- Exploration and Exploitation Problem by Wang Zhe <br />
- Exploration exploitation in Go UCT for Monte-Carlo Go <br />
- 对抗搜索、多臂老虎机问题、UCB算法 <br />
- Using Confidence Bounds for Exploitation-Exploration Trade-offs <br />
Allocation
广告流量的分配问题