Courses

Our next seminar on click fraud will be presented on March 10, 2006, in San Francisco. The presentor, Dr. Granville, is the top expert in click fraud detection and creator of patent-pending click scoring technology. He has more than 12 years of experience, including credit card fraud detection with Visa and click scoring with two major Internet companies, and post-doctorate at Cambridge University (England). Exact location and time are not yet determined. If you would like to participate, please contact us via

http://datashaping.com/security.shtml

ABSTRACT

How to Address Click Fraud in Pay-Per-Click Programs?

The problem of click fraud and non valid clicks is nearly as old as paid-per-click advertising. Only recently has it been acknowledged by major search engine companies. It represents the most serious threat to the online advertising industry. Although there is no formal definition to click fraud, here is a good description of click fraud.

We review various state-of-the-art solutions to address click fraud in pay-per-click programs, 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.

TOPICS COVERED

• Obtaining refunds from credit card companies
• Click fraud: Yahoo vs. Google
• Advertiser server logs: tagging systems to correctly track click activity
• Identifying unique users in server logs
• Google clicks not found in server logs: how big is the problem? How to fix it?
• Analytics: decision trees
• Analytics: comparison of statistical methodologies
• Analytics: tree farms and other boosted trees
• How to identify fraud hiding behind AOL proxies?
• Click scoring: logical scores tied to ROI and conversion rates
• Metric selection: velocity, delta, binned metrics; optimum binning
• How to design an alarm system
• Testing ad campaigns, click fraud entrapment
• Keyword purchase optimization to minimize fraud and increase ROI
• Reconciliation: server logs vs. Google reports
• Case studies
• Statistical analysis of Google and Yahoo reports to detect abnormalities
• Types of fraud and ad-hoc detection strategies

Register at http://datashaping.com/security.shtml