An Open Source Advertisement System

Authors: Pushkar Umaranikar, Chris Pollett

Abstract:

An online advertisement system and its implementation for the Yioop open source search engine are presented. This system supports both selling advertisements and displaying them within search results. The selling of advertisements is done using a system to auction off daily impressions for keyword searches. This is an open, ascending price auction system in which all accepted bids will receive a fraction of the auctioned day’s impressions. New bids in our system are required to be at least one half of the sum of all previous bids ensuring the number of accepted bids is logarithmic in the total ad spend on a keyword for a day. The mechanics of creating an advertisement, attaching keywords to it, and adding it to an advertisement inventory are described. The algorithm used to go from accepted bids for a keyword to which ads are displayed at search time is also presented. We discuss properties of our system and compare it to existing auction systems and systems for selling online advertisements.

Keywords: Online markets, online ad system, online auctions, search engines.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1339265

References:

[1] Y. Che and I. Gale. Expected Revenue of All-Pay and First-Price Sealed-Bid Auctions with Budget Constraints. Economics Letters. 1996. Vol. 50. pp. 373–379.
[2] Mung Chiang. Networked Life: 20 Questions and Answers. Cambridge University Press, New York. 2012.
[3] Dino Grandoni. AOL in Deal With Microsoft to Take Over Display Ad Business. Technology Section. New York Times. June 29, 2015.
[4] C. Karande, A. Mehta, R. Srikant. Optimizing Budget Constrained Spend in Search Advertising. Sixth ACM International Conference on Web Search and Data Mining, WSDM 2013, ACM, pp. 697–706.
[5] A. Mehta, A. Saberi, U. Vazirani, and V. Vazirani. AdWords and Generalized Online Matching. Journal of the ACM. Volume 54, Number 5. 2007.
[6] ComScore Inc (2011) “The 2010 U.S. Digital Year in Review” (Press Release) Retrieved on May 1, 2015 from, http://www.comscore.com/Insights/Press-Releases/2011/2/ comScore-Releases-The-2010-U.S.-Digital-Year-in-Review
[7] Google Inc. Google AdWords. Retrieved on Dec. 29, 2015 from, http: //www.google.com/about/company/history/.
[8] Google Inc. Google AdWords. Retrieved on May 1, 2015 from, https: //www.google.com/adwords/
[9] V. Krishna. Auction Theory, 2nd Ed. Academic Press. 2010.
[10] Donald R. Lehmann and Charles B. Weinberg. Sales through Sequential Distribution Channels: An Application to Movies and Videos. Journal of Marketing. Vol. 64, No. 3 (Jul., 2000), pp. 18–33.
[11] B. O’Neill. International escalation and the dollar auction. Journal of Conflict Resolution. Vol 30. pp. 33–50.
[12] J. Nielsen. Why You Only Need to Test with 5 Users. March 19, 2000. Retrieved on Dec 27, 2015 from https://www.nngroup.com/articles/ how-many-test-users/.
[13] J. Nielsen. Usability 101: Introduction to Usability. January 4, 2012. Retrieved on Dec 27, 2015 from https://www.nngroup.com/articles/ usability-101-introduction-to-usability/
[14] Sagin, Erin (January 22, 2014).“All About AdChoices: What is AdChoices? How Does it Affect Advertisers and Consumers?” WordStream. Retrieved on May 1, 2015
[15] Bing Ads Help. Microsoft. Retrieved on Dec. 28, 2015 from http://help. bingads.microsoft.com/
[16] Google Inc. Inside AdSense. Retrieved on Apr 30, 2015 from, http: //adsense.blogspot.com/
[17] Bradley Johnson (December 8, 2013). 10 Things You Should Know About Global Ad Market. Retrieved on May 1, 2015 from, http://adage. com/article/digital/online-measurement-16-web-clicking-display-ads/ 139367/
[18] Apache JMeter Retrieved on Apr 30, 2015 from, http://jmeter.apache. org/usermanual/index.html
[19] Seekquarry/Yioop About Page. Retrieved on Apr 30, 2015, from, http: //www.seekquarry.com/p/About