Precision Recruiting
Topics Covered
Seminar Fees
In the Press
SE Rankings
Site Map
 [ Home
 [ Finance ]  
 [ Web Audit ] 
 [ Consulting

Click Quality: A Better Way To Detect Click Fraud And Optimize Your Web Traffic

Upcoming seminar: San Francisco / contact us for details

Do You...

  • Want to create better tools for detecting click fraud?
  • Increase your advertising ROI?
  • Learn how to use the same techniques credit card companies use to fight fraud and maximize their ROI?
If you answered "yes" to any of these questions, then we can teach you how you can achieve your goals by using our Click Quality scoring system.

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.

The Seminar

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

  • Identifying unique users in server logs
  • Analytics: decision trees (*)
  • Analytics: comparison of statistical methodologies (*)
  • Analytics: tree farms and other boosted trees (*)
  • 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
  • Case studies
  • Statistical analysis of Google and Yahoo reports to detect abnormalities
  • How to identify fraud hiding behind AOL and other proxies? (*)
  • Types of fraud and ad-hoc detection strategies
  • Advertiser training: tagging systems to correctly monitor click activity
  • Advertiser training: missing clicks in server logs - explanation, quick fix.
  • Detecting bogus conversions
  • Problems with click monitoring systems based on Javascript and clear gif
  • Spoofed IP addresses
(*) In advanced seminar only

Why Choose Our Seminar?

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:

  • Reconcile nearly 100% of differences between your own web traffic reporting system and search engine reporting.
  • Create detailed, dollar value reporting for each one of your clicks.
  • Use data mining to cross reference conversions with IP addresses, traffic sources and keywords selected.


  • From $195 to $995 depending on the type of seminar. For details, contact us via our web form below.
  • Try our 1-hour phone consultation for $195.
  • Satisfied clients include

    • Todd Watts - Director of Marketing, GoWholeSales
    • Gary Kremen - Founder,
    • Arnaud Fisher - Product Manager, InfoSpace
    • Eric Jamieson - Director of Analytics, LowerMyBills
    • Corporate Counsel - major internet company

  • Check, credit card, wires accepted.

 Enter your e-mail address: Your status: Seminar:  


Contact us if you wish to sponsor this event. The following companies are currently sponsors:

Data Mining Machine Learning Analytics Quant Statistics Econometrics Biostatistics Web Analytics Business Intelligence Risk Management Operations Research AI Predictive Modeling Actuarial Sciences Statistical Programming Customer Insight Data Modeling Competitive Intelligence Market Research Information Retrieval Computer Science Retail Analytics Healthcare Analytics ROI Optimization Design Of Experiments Scoring Models Six Sigma SAS Splus SAP ETL SPSS CRM Cloud Computing Electrical Engineering Fraud Detection Marketing Databases Data Analysis Decision Science Text Mining