• Corpus ID: 3937756

Machine Learning in Online Advertising held in conjunction with the 24 th Annual Conference on Neural Information Processing Systems

  title={Machine Learning in Online Advertising held in conjunction with the 24 th Annual Conference on Neural Information Processing Systems},
  author={Deepak K. Agarwal and Deepak K. Agarwal and Tie-Yan Liu and Tao Qin and James G. Shanahan},
Most on-line advertisements are display ads, yet as compared to sponsored search, display advertising has received relatively little attention in the research literature. Nonetheless, display advertising is a hotbed of application for machine learning technologies. In this talk, I will discuss some of the relevant differences between online display advertising and traditional advertising, such as the ability to profile and target individuals and the associated privacy concerns, as well as… 

Figures and Tables from this paper


Search advertising using web relevance feedback
Empirical evaluation based on over 9,000 query-ad pairwise judgments confirms that using augmented queries produces highly relevant ads.
Contextual advertising by combining relevance with click feedback
This paper shows how this match between individual ads and the content of the page where the ads are shown can be improved significantly by augmenting the ad-page scoring function with extra parameters from a logistic regression model on the words in the pages and ads.
Exploitation and exploration in a performance based contextual advertising system
This paper develops two novel EE strategies for online advertising that can adaptively balance the two aspects of EE by automatically learning the optimal tradeoff and incorporating confidence metrics of historical performance.
A semantic approach to contextual advertising
A system for contextual ad matching based on a combination of semantic and syntactic features is proposed, which will help improve the user experience and reduce the number of irrelevant ads.
How much can behavioral targeting help online advertising?
This work is the first empirical study for BT on the click-through log of real world ads and draws three important conclusions: users who clicked the same ad will truly have similar behaviors on the Web, Click-Through Rate (CTR) of an ad can be averagely improved as high as 670% by properly segmenting users for behavioral targeted advertising in a sponsored search.
To swing or not to swing: learning when (not) to advertise
This paper proposes two methods for addressing the decision problem "whether to swing", whether or not to show any of the ads for the incoming request, a simple thresholding approach and a machine learning approach, which collectively analyzes the set of candidate ads augmented with external knowledge.
Catching the drift: learning broad matches from clickthrough data
An online learning algorithm, Amnesiac Averaged Perceptron, that is highly efficient yet able to quickly adjust to the rapidly-changing distributions of bidded keywords, advertisements and user behavior is presented.
Predicting clicks: estimating the click-through rate for new ads
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.
Personalized click prediction in sponsored search
This paper develops user-specific and demographic-based features that reflect the click behavior of individuals and groups in sponsored search and demonstrates that the personalized models significantly improve the accuracy of click prediction.
A Markov chain model for integrating behavioral targeting into contextual advertising
A new notion of relevance between webpages and ads based on users' online click-through behaviors from BT's perspective is proposed, and a combination model integrating behavioral relevance and contextual relevance for matching ads and webpags is presented.