Advanced search
1 file | 1.87 MB

Born to trade: a genetically evolved keyword bidder for sponsored search

Author
Organization
Abstract
In sponsored search auctions, advertisers choose a set of keywords based on products they wish to market. They bid for advertising slots that will be displayed on the search results page when a user submits a query containing the keywords that the advertiser selected. Deciding how much to bid is a real challenge: if the bid is too low with respect to the bids of other advertisers, the ad might not get displayed in a favorable position; a bid that is too high on the other hand might not be profitable either, since the attracted number of conversions might not be enough to compensate for the high cost per click. In this paper we propose a genetically evolved keyword bidding strategy that decides how much to bid for each query based on historical data such as the position obtained on the previous day. In light of the fact that our approach does not implement any particular expert knowledge on keyword auctions, it did remarkably well in the Trading Agent Competition at IJCAI2009.

Downloads

  • borntotrade.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 1.87 MB

Citation

Please use this url to cite or link to this publication:

Chicago
Munsey, Michael, Jonathan Veilleux, Sindhura Bikkani, Ankur Teredesai, and Martine De Cock. 2010. “Born to Trade: a Genetically Evolved Keyword Bidder for Sponsored Search.” In IEEE Congress on Evolutionary Computation. New York, NY, USA: IEEE.
APA
Munsey, M., Veilleux, J., Bikkani, S., Teredesai, A., & De Cock, M. (2010). Born to trade: a genetically evolved keyword bidder for sponsored search. IEEE Congress on Evolutionary Computation. Presented at the 2010 IEEE World congress on Computational Intelligence (WCCI 2010), New York, NY, USA: IEEE.
Vancouver
1.
Munsey M, Veilleux J, Bikkani S, Teredesai A, De Cock M. Born to trade: a genetically evolved keyword bidder for sponsored search. IEEE Congress on Evolutionary Computation. New York, NY, USA: IEEE; 2010.
MLA
Munsey, Michael, Jonathan Veilleux, Sindhura Bikkani, et al. “Born to Trade: a Genetically Evolved Keyword Bidder for Sponsored Search.” IEEE Congress on Evolutionary Computation. New York, NY, USA: IEEE, 2010. Print.
@inproceedings{1108124,
  abstract     = {In sponsored search auctions, advertisers choose a set of keywords based on products they wish to market. They bid for advertising slots that will be displayed on the search results page when a user submits a query containing the keywords that the advertiser selected. Deciding how much to bid is a real challenge: if the bid is too low with respect to the bids of other advertisers, the ad might not get displayed in a favorable position; a bid that is too high on the other hand might not be profitable either, since the attracted number of conversions might not be enough to compensate for the high cost per click.
In this paper we propose a genetically evolved keyword bidding strategy that decides how much to bid for each query based on historical data such as the position obtained on the previous day. In light of the fact that our approach does not implement any particular expert knowledge on keyword auctions, it did remarkably well in the Trading Agent Competition at IJCAI2009.},
  author       = {Munsey, Michael and Veilleux, Jonathan and Bikkani, Sindhura and Teredesai, Ankur and De Cock, Martine},
  booktitle    = {IEEE Congress on Evolutionary Computation},
  isbn         = {9781424481262},
  language     = {eng},
  location     = {Barcelona, Spain},
  pages        = {8},
  publisher    = {IEEE},
  title        = {Born to trade: a genetically evolved keyword bidder for sponsored search},
  url          = {http://dx.doi.org/10.1109/CEC.2010.5585963},
  year         = {2010},
}

Altmetric
View in Altmetric
Web of Science
Times cited: