Practical Lessons from Predicting Clicks on Ads at Facebook

@inproceedings{He2014PracticalLF,
  title={Practical Lessons from Predicting Clicks on Ads at Facebook},
  author={Xinran He and Junfeng Pan and Ou Jin and Tianbing Xu and Bo Liu and Tao Xu and Yanxin Shi and Antoine Atallah and Ralf Herbrich and Stuart Bowers and Joaquin Qui{\~n}onero Candela},
  booktitle={ADKDD'14},
  year={2014}
}
Online advertising allows advertisers to only bid and pay for measurable user responses, such as clicks on ads. [...] Key Result Picking the optimal handling for data freshness, learning rate schema and data sampling improve the model slightly, though much less than adding a high-value feature, or picking the right model to begin with.Expand
Modern Models for Learning Large-Scale Highly Skewed Online Advertising Data
TLDR
A comprehensive summary of the state-of-art machine learning models (decision tree based, regularized logistic regression, online learning, and factorization machine) that are often used in the industry to solve the problem of click through rate and conversation rate estimation. Expand
User Response Learning for Directly Optimizing Campaign Performance in Display Advertising
TLDR
This paper reformulates a common logistic regression CTR model by putting it back into its subsequent bidding context: rather than minimizing the prediction error, the model parameters are learned directly by optimizing campaign profit. Expand
CLR: coupled logistic regression model for CTR prediction
TLDR
Experimental results on real-world data set show that the proposed novel model, Coupled Logistic Regression (CLR), can guarantee both accuracy and efficiency on large scale CTR prediction problems. Expand
Click-through Prediction for Advertising in Twitter Timeline
TLDR
A learning-to-rank method is proposed which not only addresses the sparsity of training signals but also can be trained and updated online and its superiority over the current production model adopted by Twitter is demonstrated. Expand
Research on Click-Through Rate Prediction in Display Advertising Based on Machine Learning
Display ads are an important part of online advertising. Predicting clicks before a display ad can not only reduce the cost of ad serving but also increase the efficiency of Internet companies’Expand
Click Maximization in Online Social Networks Using Optimal Choice of Targeted Interests
TLDR
A greedy algorithm and a genetic algorithm are proposed to find near-optimal combinations of conceptual nodes in polynomial time, with the genetic algorithm nearly matching the optimal solution. Expand
An Embedded Model XG-FwFMs for Click-Through Rate
TLDR
A embedded model named XG-FwFMs which use less parameters calculating and prevent the model from over-fitting is proposed which has better prediction accuracy, parameter sensitivity and effectiveness than traditional nonlinear models. Expand
Attention Convolutional Neural Network for Advertiser-level Click-through Rate Forecasting
TLDR
This work proposes a novel context-aware attention convolutional neural network (CACNN), which can capture the high non-linearity and local information of the time series, as well as the underlying correlation between the timeseries of CTR and the contextual information. Expand
Feature Engineering of Click-through-rate Prediction for Advertising
TLDR
This paper proposes some feature engineering methods based on gradient boosting decision tree (GBDT) and Bayesian smoothing to obtain a wonderful feature, which has more useful information and is not so sparse. Expand
Ranking Models for Ads at Yelp
Predicting the click-through rate (CTR) of online advertisements lies at the heart of the business model of many of the world’s biggest Internet-based companies like Google, Facebook, or Twitter.Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 13 REFERENCES
Ad click prediction: a view from the trenches
TLDR
The goal of this paper is to highlight the close relationship between theoretical advances and practical engineering in this industrial setting, and to show the depth of challenges that appear when applying traditional machine learning methods in a complex dynamic system. Expand
Predicting clicks: estimating the click-through rate for new ads
TLDR
This work shows that it can be used to use features of ads, terms, and advertisers to learn a model that accurately predicts the click-though rate for new ads, and shows that using this model improves the convergence and performance of an advertising system. Expand
Predictive model performance: offline and online evaluations
TLDR
A new model evaluation paradigm is designed that simulates the online behavior of predictive models and results are highly promising on click prediction model for search advertising. Expand
Web-Scale Bayesian Click-Through rate Prediction for Sponsored Search Advertising in Microsoft's Bing Search Engine
TLDR
A new Bayesian click-through rate (CTR) prediction algorithm used for Sponsored Search in Microsoft's Bing search engine is described, based on a probit regression model that maps discrete or real-valued input features to probabilities. Expand
Data warehousing and analytics infrastructure at facebook
TLDR
This paper presents how Scribe, Hadoop and Hive together form the cornerstones of the log collection, storage and analytics infrastructure at Facebook and enabled us to implement a data warehouse that stores more than 15PB of data and loads more than 60TB of new data every day. Expand
Greedy function approximation: A gradient boosting machine.
Function estimation/approximation is viewed from the perspective of numerical optimization in function space, rather than parameter space. A connection is made between stagewise additive expansionsExpand
An Empirical Evaluation of Thompson Sampling
TLDR
Empirical results using Thompson sampling on simulated and real data are presented, and it is shown that it is highly competitive and should be part of the standard baselines to compare against. Expand
Photon: fault-tolerant and scalable joining of continuous data streams
TLDR
The architecture of Photon is described, a geographically distributed system for joining multiple continuously flowing streams of data in real-time with high scalability and low latency, where the streams may be unordered or delayed. Expand
Processing Sliding Window Multi-Joins in Continuous Queries over Data Streams
TLDR
It is shown that hash joins are faster than NLJs for performing equi-joins, and that the overall processing cost is influenced by the strategies used to remove expired tuples from the sliding windows. Expand
Adaptive Algorithms and Stochastic Approximations
TLDR
The juxtaposition of these two expressions in the title reflects the ambition of the authors to produce a reference work, both for engineers who use adaptive algorithms and for probabilists or statisticians who would like to study stochastic approximations in terms of problems arising from real applications. Expand
...
1
2
...