Yesterday a 47-page report on Google’s Click Fraud problem was released by an independent expert, Dr. Alexander Tuzhilin, a professor at NYU. Google also produced it’s own findings and both documents were summerized by Matt Cutts who works for Google.
While Matt Cutts may have spent much of Saturday reading both documents - I took a shortcut, I admit - by using Pertinence Summarizer - which I have found particularly effective for Search Engine Work; it also helps summarize with long documents, probably better than any other summarizer I have come across. - I can often get to the heart of a document in a couple of minutes rather than a couple of hours.
Of Dr. Alexander Tuzhilin’s findings on Click Fraud:
"…[Click Fraud detection can not] be operationalized in the sense that invalid click detection methods can be developed that would algorithmically identify invalid and only invalid clicks satisfying these definitions
"First of all, to determine if a certain click is invalid, it is necessary to understand the intent of generating the click: was the click generated “artificially” (improperly) or not and what does exactly “artificial” mean in this case." However, Google does not have full knowledge of which clicks are actually valid and invalid, and it is impossible to identify performance rates of the filters without this knowledge. Significant progress has been made in combating invalid clicking activities and developing mature systems and processes to accomplish this task.
- using certain types of software bots (to produce)clicks on Google’s ads on the publisher’s own web site constitute examples of such “prohibited means” and can be detected using technological means and marked as “invalid”. An Auto-Termination System is employed - an automated offline system for detecting the AdSense publishers who are engaged in inappropriate behavior violating the Terms and Conditions of the AdSense program.
I suspect that Google looks for a bot coming from a related IP Address or subnet where the pulishers site is on and will disqualify those clicks - if it determines they are produced by an automated program.
However, there are times when people will click on an ad twice for totally valid reasons and in this case, Google does not consider this Click Fraud.
-a person might have clicked on an ad, looked at it, went somewhere else but then decided to have another look at the ad shortly thereafter to make sure that he/she got all the necessary information from the ad (i have done the same thing myself).
-…filters simply don’t know if the conversion will take place or not by the time they need to make the decision. Since these clicks cannot be safely removed by filters, the filters pass them as valid, and it is the job of alerts to identify them in the offline analysis stage and pass these suspicious clicks to human experts for manual investigations.
-Still, despite its noticeable negative effects on its financial performance, Google decided to abandon the old doubleclick policy and not to charge advertisers for the second click, which was an appropriate action to take
There’s a Click Quality Team at Google that tries to figure out if any of the invalid Clicks are valid, and if they are not, the advertisers should not have to pay for those clicks.
"Using various data mining methods, one can build a statistical (data mining) model based on the past data that can classify new clicks into valid or invalid and also assign some degree of certainty (probability) to this classification."
-Pre-Filtering. Certain clicks are removed immediately from the logs before they are even “seen” by the online filters. However, new and better filters will require a more powerful computing infrastructure than is currently available, and the Click Quality team also participates in developing this infrastructure. Google provides several filters (with thresholds) that are applied one after another (sorta reminds me of Sendmail).
In addition, when complaints are investigated they come about through two avenues:
Advertiser complaints: an advertiser notices unusual clicking activities and requests Google to investigate those activities for the presence of invalid clicks.
Publisher’s complaint: publisher notices some suspicious activities on his/her site and asks Google to investigate them.
Once such deviations are discovered, the investigator “drills down” into the problem and uncovers the reasons causing these deviations and, most likely, the source and reasons for the inappropriate activity or a set of activities. The outcomes of these investigations is the determination of whether
I got to all of this in about 20 minutes of my time using Pertinence Summerizer - perhaps I would have gotten more out of reading the whole document but I don’t have 3 hours to spend right now.
\
Current Subscribers
