Learning optimally from self-interested data sources in on-line ad auctions
See Also:
Download slides:
bsciw08_zoeter_lofsdsioao_01.pdf (541.2 KB)
Launch in a standalone WM Player
Switch to Windows Media Player
Related content
30:10
289 views - Jason D. Hartline, 2008
18:43
35 views - Onno Zoeter, 2009
40:35
24 views - Onno Zoeter, 2005
58:28
92 views - Michael Schwarz, 2008
59:05
143 views - Chris Burges, 2008
05:14
100 views - Anton Schwaighofer, 2008
01:17:48
6254 views - Isabelle Guyon, 2007
22:07
29 views - Onno Zoeter, Michael Schwarz, Jason D. Hartline, Anton Schwaighofer, 2008
01:37:46
2588 views - Adam Kalai, 2005
59:02
163 views - Michael Schwarz, 2008
Report a problem or upload files
If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Description
In the analysis of current online ad auctions essential parameters such as click-through rates are often assumed to be known. The disregard of the uncertainty that is present in reality leads to several serious problems. In the talk we will highlight two: (i) there is no principled exploration of new ads, and (ii) there is no incentive for advertisers to only subscribe to well targeted key-words. In fact, there is an interesting opportunity for very poorly targeting advertisers to exploit this fact. We present a new auction that solves both problems. The key trick for this auction is that advertisers are not only requested to submit a bid, but also a belief over their own click-through rate.
Link this page
Would you like to put a link to this lecture on your homepage?Go ahead! Copy the HTML snippet !




Write your own review or comment: