2017 AdKDD & TargetAd
in conjunction with
The 23rd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2017)
Looking for this year?
Visit http://www.adkdd.org
August 14, 2017
Halifax, Nova Scotia, Canada
An average consumer today spends 8+ hours across all devices, interacting with online content almost entirely sponsored by advertisements. At projected $300B market share by 2020, online advertising and computation advertising in particular is perhaps the most visible and ubiquitous application of machine learning, and one that interacts directly with consumers. When done right ads help us enrich our lives, and creep us out when done poorly.
​
Looking at the published literature over the last few years, many researchers might consider computational advertising as a mature field. Yet, quite the opposite is true. Computational advertising is constantly evolving, transforming from ads controlled by monolithic publishers and randomly rotating banner ads to highly personalized content experiences in new feeds on mobile devices and even on TV. Computational targeting systems are trained on petabytes of data amassed from thousands of hours of online user activities, with these numbers growing larger by the day. Targeted ads are far from done.
​
There has been a total of ten AdKDD and TargetAd workshops to date, organized every year since 2007, which focused on highlighting state-of-the-art advances in computational advertising. All the workshops were well attended, often with standing room only, and very well received both by the academic community and the advertising industry. Motivated by these successes, for 2017 we are happy to announce a joint edition of AdKDD and TargetAd, which we believe will bring an even stronger program than the past years. We look forward to seeing you in Halifax to discuss the past, present, and future of computational advertising!
​
Program
Session 1
8:00 AM - 10:00 AM
8:00 - 8:20
Paper: Optimal Reserve Price for Online Ads Trading Based on Inventory Identification
8:20 - 8:40
Paper: MM2RTB: Bring Multimedia Metrics to Real-Time Bidding
8:40 - 9:00
Paper: Data-Driven Reserve Prices for Social Advertising Auctions at LinkedIn
​
9:00 - 9:20
Paper: Cost-sensitive Learning for Utility Optimization in Online Advertising Auctions
​
9:20 - 10:00
Invited Talk: Randall Lewis (Netflix)
Title: Incrementality Bidding & Attribution
Coffee Break
10:00AM - 10:30AM
​
Session 2
10:30 AM - 12:00 PM
10:30-11:20
Invited Talk: Susan Athey (Stanford)
Title: Machine Learning & Causal Inference for Advertising Effectiveness
11:20-11:40
Paper: Blacklisting the Blacklist in Online Advertising
11:40-12:00
Paper: Anti-Ad Blocking Strategy: Measuring its True Impact
Lunch
12:00PM-1:00PM
​
Session 3
1:00 PM - 3:00 PM
1:00-1:20
Paper: An Ensemble-based Approach to Click-Through Rate Prediction for Promoted Listings at Etsy
1:20-1:40
Paper: A Practical Framework of Conversion Rate Prediction for Online Display Advertising
1:40-2:00
Paper: Deep & Cross Network for Ad Click Predictions
​
2:00-2:20
Paper: Profit Maximization for Online Advertising Demand-Side Platform
​
2:20-3:00
Invited Talk: Alex Smola (Amazon)
Title: Users & Time
Coffee Break
3:00PM-3:30PM
​
Session 4
3:30 PM - 5:30 PM
3:30-4:10
Invited Talk: Thorsten Joachims (Cornell)
Title: Learning from Logged Interventions
4:10-4:30
Paper: Attribution Modeling Increases Efficiency of Bidding in Display Advertising
4:30-4:50
Paper: Ranking and Calibrating Click-Attributed Purchases in Performance Display Advertising
4:50-5:00
Best Paper Award & Conclusion
Call for Papers
Important Dates
Submission
May 28, 2017
Decision
June 16, 2017
Camera-ready
July 6, 2017
Workshop
August 14, 2017
Description
The workshop focuses on three main aspects of computational advertising.
​
-
Evolution of computational advertising: Online advertising has progressed beyond the notion of traditional desktop ads to ads that are native, social, mobile, and contextual. In tandem, the rise of new mechanisms, such as header bidding, complex ad exchanges, repeated auctions, ad blockers, viewability trackers and others, challenge the traditional notions of advertising. There also continues to exists controversial issues in advertising such as privacy, security, fraud, ethics, and economic attribution. We invite papers that are focused on some of the above aspects.
​
-
Large-scale and novel ad targeting: Recent advances in real-time, bid data systems, and easier accessibility to different types of data make it possible to design more personalized and efficient ad targeting systems. We invite papers that advance the state-of-the-art in related areas of ad targeting.
​
-
Deployed systems & battle scars: We particularly encourage papers that highlight experience in deploying real-time ad targeting systems, data and audience insights, as well as position papers on the future of online advertising.
Submission Instructions
Following KDD conference tradition, reviews are single-blind, and author names and affiliations should be listed. Submitted papers will be assessed based on their novelty, technical quality, potential impact, insightfulness, depth, clarity, and reproducibility. For each accepted paper, at least one author must attend the workshop and present the paper.
​
Submissions are limited to a total of six pages, including all content and references, must be in PDF format, and formatted according to the new Standard ACM Conference Proceedings Template . Additional information about formatting and style files is available here.
​
​
Call for Papers
Important Dates:
Submission Deadline Extended!
Submission -- Extended!
June 4, 2017
Decision
June 16, 2017
Camera-ready
July 9, 2017
Workshop
August 14, 2017
Description
The workshop focuses on three main aspects of computational advertising.
​
-
Evolution of computational advertising: Online advertising has progressed beyond the notion of traditional desktop ads to ads that are native, social, mobile, and contextual. In tandem, the rise of new mechanisms, such as header bidding, complex ad exchanges, repeated auctions, ad blockers, viewability trackers and others, challenge the traditional notions of advertising. There also continues to exists controversial issues in advertising such as privacy, security, fraud, ethics, and economic attribution. We invite papers that are focused on some of the above aspects.
​
-
Large-scale and novel ad targeting: Recent advances in real-time, big data systems, and easier accessibility to different types of data make it possible to design more personalized and efficient ad targeting systems. We invite papers that advance the state-of-the-art in related areas of ad targeting.
​
-
Deployed systems & battle scars: We particularly encourage papers that highlight experience in deploying real-time ad targeting systems, data and audience insights, as well as position papers on the future of online advertising.
Submission Instructions
Following KDD conference tradition, reviews are single-blind, and author names and affiliations should be listed. Submitted papers will be assessed based on their novelty, technical quality, potential impact, insightfulness, depth, clarity, and reproducibility. For each accepted paper, at least one author must attend the workshop and present the paper.
​
Submissions are limited to a total of six pages, including all content and references, must be in PDF format, and formatted according to the new Standard ACM Conference Proceedings Template. Additional information about formatting and style files is available here.
​
Best Paper Award
Thanks to a generous contribution from Criteo Research we will be awarding USD1000 to the best paper and USD 500 to the runner up.
​
​
