Link is to a press release with a light summary, the research paper is here: http://www.cs.utexas.edu/~vacha/ccs13.pdf
Simple and apparently extremely effective idea for combating click fraud, just consider anything with bad ROI for the advertiser to be click fraud. This kind of reminds me of Google's approach to e-mail spam, saying that spam is anything someone doesn't want. There's a general idea here, if a problem is hard, it may be certain types of errors you make really don't matter, which might let you solve some much easier problem.
<p>When is a click not a click? When an advertising network registers a click on one of their online advertisements, how can it be sure that a single consumer – a “pair of eyeballs” in Madison Avenue jargon – and not a malware computer program, is behind that one click? Or that the viewer’s click was intentional, not induced by deceptive or misleading advertising?</p>
Add a comment...