|
|
|
| Presenter |
| Topics Covered |
| Audience |
| Seminar Fees |
| Register |
| In the Press |
| SE Rankings |
| * |
| Site Map |
|
|
|
|
|
Click Quality: A Better Way To Detect Click Fraud And Optimize Your Web Traffic
Whether you are a product manager, search marketer or analyst, if you make business decisions that affect ROI or involve handling click fraud, then you need to learn about Click Quality. Click Quality Click fraud is a growing concern in pay-per-click advertising. Some call it an ecosystem tax. Others call it a looming crisis that will ruin Google and Yahoo. Years of experience in helping both advertisers and search engines has led us to look at the subject in another way. The phrase "click fraud" is misleading. It is true that thousands of unethical individuals are gaming various search engines and cheating advertisers. But how you can really be sure that any given click is fraudulent? You can't. The sheer volume of data you're collecting makes it impossible to know the true nature of any individual click. To solve this problem, advertisers and search engines use sets of rules to distinguish "good" clicks from "bad" clicks. But these rules-based systems often break down as traffic grows and are not effective in dealing with new types of data. The result is false positives or worse, missing new types of fraud. Our approach is to use data mining to identify patterns and assign a quality score to each click. This is how banks and credit companies manage the risk of issuing credit cards. By constantly analyzing their data, they can assess how likely an individual credit card user is to default on their payments or engage in fraud and assign a value to the user. We've discovered the same concept can be applied to analyzing clicks. As a result, our techniques are more accurate and adapt to changes much more quickly than rules based systems.
Our goal is to help both search engines and advertisers. We all have a common interest in maximizing the value of web traffic. Search engines need advertisers to support their business. Advertisers need search engines to acquire new customers. Together, we will review various state-of-the-art solutions to address Click Quality in pay-per-click advertising, including proprietary IP blacklists, entrapment, ad-hoc design of experiment and detection of false positives. Our core contribution is a scoring system tied to the advertiser's ROI and matching conversion rate distributions. New original fraud cases will be discussed, including impression and ad relevancy fraud, automated clicks from shareholders and political activists, and accidental click fraud generated by email spammers harvesting email addresses.
Topics Covered
Our clients include major search engines and advertisers like InfoSpace, CNET and LowerMyBills. The Click Quality system was developed by our presenter, one of the top experts in click fraud detection, Dr. Vincent Granville. Dr. Granville earned his post-doctorate in Statistics at England's Cambridge University. After spending two years working in Visa's credit card fraud detection unit, he began advertising his services on various search engines. In 2003, sensing a need in the market, he also became the first advertiser to purchase the keywords "click fraud" on Google and Yahoo. No one else will teach you how to:
 Fees
Sponsors Contact us if you wish to sponsor this event. The following companies are currently sponsors:
|