Fair Isaac Click Fraud Study

I was very fortunate to have a discussion with Joseph Milana from the research department of Fair Isaac on a click fraud study they are currently running. 

Fair Isaac is a company which supplies business intelligence product across a wide range of business sectors, the product they are most well know for is Falcon Fraud Manager which protects 20 of the worlds top 25 financial institutions against credit and debit card fraud. 

Fair Isaac's core competency is the analysis of large data sets, the data mining they do gives them the ability to do deep statistical analysis looking for patterns which appear pathological.  Using their knowledge and techniques to spot fraud in the credit card arena, the are performing a study into click fraud.

Fair Isaac have issued a call to the broader ppc advertising community to supply data with which they can complete a very detailed analysis of click fraud in an attempt to ascertain if there is a real problem. I have agreed to help them collect this type of data through a call to action of this blogs readership to supply data for their study.

They require the following atomic level data and most saliently, after click information i.e. did the click convert   The items marked in bold are required, the others are would like to have:

- Session ID

· Date-time of visit

· URL referrer (particularly relevant for tracking the traffic arising from affiliates)

· Client IP address

· URI Stem (the page accessed)

· User Agent (browser related data used by the client)

· Advertising Campaign (including Publisher)

· Keyword

· Daily spend limit

· Click cost

· Link ranking (i.e., w.r.t. the placement of the ad on whatever page by the Search Engines)

· Conversion Indicator

· Total time of the session

· Total number of pages migrated during the Session.

The output of the study will be a report to the general market place on their click fraud findings along with a private report to each company which participates in the study.  It must be stressed that they cannot assist in any reparation of ppc fees.

If the findings are positive that click fraud is a serious issue, it is envisages that Fair Isaac will introduce a click fraud detection product.  Their thinking is to place the product at a point where click fraud is detected and advertisers are not billed rather than relying on refunds from the ppc suppliers.

Any data supplied by advertisers will be protected via an NDA (non disclosure agreement) so you can be assured that any data you supply will be treated with the strictest of confidentiality.

If you are interested in contributing to this study, please contact me in the first instance and I will put you in contact with the Fair Isaac's research team.

--

(AF) Search Engine Marketing Magazine Search Marketing Standard

Click Fraud is catered for by max CPC

I read with great interest about one commentators idea that market forces and adjustment to max cpc cancels out click fraud.

In their post the blog talk from computer to cd they state:

The key point is that click fraud is already taken into effect when advertisers select the highest amount they will bid. For instance, there is no difference whether an advertiser pays $0.83/click for 121 clicks with 21 being fraudulent, or $1.00/click for 100 clicks when there is absolutely no fraud. In either case, the advertiser pays $100 and generates a profit of $20, and Overture and/or Google make $100. What changes is the advertiser’s yield (e.g., the percent of clickers who purchased the book) which in turn effects their highest bid price. That is, with fraud, 30 out of 121 clickers (24.8%) purchased the book, and without fraud 30 out of 100 clickers (30%) purchased it. Without fraud, the bid price in an efficient market will rise from $0.83 to $1.00.

In summary, online advertisers must focus on analyzing and improving their internal metrics (e.g., conversions) and not worry about click fraud as it is already incorporated into keyword bid prices. Hopefully, the frivolous lawsuits and refund requests spawned by apparent click fraud will end as those in the industry recognize this undeniable fact.

I am not sure if this model stands up to a sustained distributed attacks from click bots, but I think this is a very interesting concept.

--
(AF) Click fraud software from Click
Tracks