We’re constantly hard at work here at Click Forensics to continuously improve our ability to accurately predict overall traffic quality for our clients.  And, every now and then, we’re able to bundle a number of these enhancements into the tangible release.  We did just that last week; announcing an upgraded version of our Yahoo! TQ Forecast feature.  We’ve been testing these features with a handful of clients, with strong results so far – namely, much better predictive accuracy so that clients can be sure they’re sending high quality/high paying traffic into Yahoo.  And, we’re excited to now be rolling this out to all our clients.  Specific features include:

• YTQ Forecast Report – provides a summary of the likely Yahoo! TQ scores particular traffic sources will receive when they’re sent to Yahoo!;
• Dynamic Adjustments - continuously monitors and adjusts to changes in the YTQ score rankings so that clients can appropriately tune and filter traffic sources;
• Preemptive Traffic Source Blocking – enables publishers and ad networks to quickly identify and block certain online advertising traffic sources that are likely to deliver low Yahoo! TQ scores; and
• Enhanced Botnet Detection – delivers better detection of non-human clicks, both malicious and benign, while serving as an early warning system for advanced sources of fraud.

We also got some nice coverage in AdExchanger about the problems some of our CPC and performance-based ad network clients face and how these new enhancement will help solve these challenges.

In February of 2006, Click Forensics was just getting off the ground.  We recognized the problem of click fraud was a big problem and that building a solution would be tough technical challenge.  We decided to bring in an expert in the field of data mining and anomaly detection in clickstream analysis.  That expert was Dr. Alex Tuzhilin.  Alex spent the day with us at our offices in San Antonio and provided us a roadmap for the evolution of our approach to indentifying invalid traffic. 

His contribution to us at that point was essential and provided tremendous insight.  After reviewing our approach he commented,

“Click Forensics has good data and this is a source of their advantage over the search engines. My role is to work with them to refine the scoring methodology to improve accuracy. Their approach is to incorporate as much data as possible to improve accuracy. The search providers simply don’t have enough data to have the most accurate approach.”

Shortly after Alex’s visit to Texas, I received a call from the lead attorney representing Lane’s Gifts in their lawsuit against Google.  He said, “Tom, I just hired your Ph.D!”  He told me that the judge in that case had mandated that an outside consultant review Google’s click fraud detection methods and publish a paper on the efficacy.  Alex spent many weeks at Google and wrote an insightful paper detailing their approach, ultimately describing it as “reasonable”.  The Lane’s Gift case was settled and Alex returned to his role as a professor at NYU.

Today we are thrilled to announce that Dr. Tuzhilin has joined the Click Forensics Advisory Board.  Few individuals have had more real-world and academic experience in the measurement of online traffic quality and its effect on advertisers.  His work has helped move the industry toward standards and cooperation.  After visiting us in Austin a few weeks ago and meeting with our technology team, Alex said,

“Having firsthand experience reviewing the state of the art in ad network traffic management, I was impressed with the level of technical sophistication the team exhibits and I was impressed with the directions they are going, Click Forensics has played a leadership role in helping the online advertising community to monitor quality of clicks on ads, including identification of invalid clicks. I look forward to continuing to work with the team.”

In addition to Dr. Tuzhilin, we have also added Dr. William Wright, the Chief Scientist at Paypal.  Dr.Wright, a Ph.D. in cognitive science, is an artificial intelligence expert who has built numerous analytical and predictive systems over the past twenty years, including the Falcon Credit Card Fraud Detection System at HNC, the Advanced Fraud Screen system at CyberSource, and numerous adversarial modeling systems for the U.S. military.  After spending time with our team, William concluded,

“Click Forensics has built a strong team of developers using very advanced machine learning and data mining techniques to detect fraud and measure traffic quality, they are pioneering a new area of fraud detection and I’m finding it satisfying to work closely with them on leveraging lessons from my past experience combating credit card and banking fraud.”

One out of every five employees at Click Forensics holds a Ph.D.  Adding the expertise of Alex and William dramatically enhances our ability to meet our goal of providing the state of the art approach to traffic quality management.  I appreciate their contributions and look forward to benefiting from their knowledge in the future.

While attendance at SES San Jose was definitely down this year, it was still a great show.  I enjoyed meeting people at our booth and appreciated the hard work of our team pulling that all together.  We met a lot of interesting folks and enjoyed hearing feedback on the new Click Forensics dashboard.

The big hit, of course, were the “Stress Einstein” squishys! Who wouldn’t want of these guys!  They reminded me of the bobble-heads in “Night at the Museum 2″  

I also enjoyed participating in a session titled, “Ads in a Quality Score World“.   Mike Grehan moderated the panel and both Yahoo (Tomaso Pozzi) and Google (Jonathan Alferness) participated.  WebProNews covered the session and wrote a nice recap. 

The other highlight of the week for me was our Click Quality Council dinner.  We had over 25 executives from ad networks, publishers, advertisers and search engines join us for a great dinner of conversation, networking and fun!

The conversation is always interesting when you have people representing all corners of the online advertising ecosystem.  It was the third year we have hosted the CQC dinner in San Jose and our 13th since the Council was formed in 2006.

Congratulations to the newlyweds… after a long, long courtship Microsoft and Yahoo finally managed to get together (the prenuptials are still being sorted out!).  I have been in favor of this union for sometime now.  Google owns a ridiculous share of the pay per click advertising market and desperately needs a competitor.  Microsoft + Yahoo = Competition.  As I have said for the last several years, the lens we look through at Click Forensics is that of the advertiser.  Competition is always good for the advertiser.  

The growth of online advertising, in particular pay per click advertising, has been meteoric. It is a great model and one that has proven hugely successful for hundreds of thousands of advertisers large and small.  It is a model that will continue to grow as large advertisers shift more dollars from unmeasureable and less effective traditional media.  It will grow because it uses context, targeting and relevancy to the highest level.  Yahoo’s audience enhanced by Microsoft’s technology will mean innovation and efficiency.  There is no doubt; Google will continue to have success.  But the new partnership will make the online world even more attractive for advertisers.

Today there are standards in place to help hold the search providers accountable.  There are better reporting, campaign management and keyword tools to add to the efficiency.  I see a world in the near future where display advertising will begin to make significant gains from the data that exists in search. Context, targeting and relevance can improve every medium and this partnership will leverage that data to a much higher level than before.

So congrats to you both for a new start.  The entire advertising community is pulling for you and expecting big things. I do need to warn you… expectations are high and the honeymoon is short.  

We recently launched a new reporting interface for our ad network customers to provide more actionable insights into downstream publisher sources. The early feedback from new adopters has been very positive. In this blog post, I will provide a brief overview of the new enhancements.

So, why did we decide to roll out a new reporting platform? As we are growing with our customers, we learned to better understand their most pressing business problems and how our products can help address those. Downstream publisher management and new publisher screening are critical to daily operations of ad networks. We were looking for new ways to tackle them in a more effective manner.

Based on insightful customer feedback we had received, we worked on the new reporting interface with the following design goals in mind:

• Present actionable insights into large volumes of click data to better highlight traffic quality from downstream publisher sources
• Easily handle daily click volumes of 10 million clicks and deliver sub-second interface response times
• Provide detailed background information about new publishers during the approval process before accepting traffic

Users of the new interface are greeted by the publisher dashboard that summarizes current network and publisher activity. It is the starting point for further investigation. At a glance, ad network staff find their top publishers sorted by different attributes, for example by volume and traffic. The “Movers and Shakers” sections highlight sources with significant traffic changes in certain dimensions. Here is a screenshot of the dashboard:

Throughout the interface, we added small sparklines to offer traffic information at a glance without having to leave the page. For example, an average click score is accompanied by a score histogram (see this previous post for more details) and a volume volatility graph. These cues help users to absorb the information more quickly and spot areas that warrant further investigation:

Another tab in the interface offers publisher screening capabilities. It supports ad networks in making better decisions about which publisher applications to approve before accepting any traffic. After entering a URL, a report will present detailed background information about the specific domain, combining reputation information from the Click Forensics community database and public sources like Alexa, Compete.com and whois.

Next to the highlighted features, we have added numerous other useful capabilities for our customers. The new reporting interface is now available to all of our ad network customers. If you would like to learn more please don’t hesitate to contact us.

Over the past week four major players in the online media space have announced accreditation to the Interactive Advertising Bureau’s Click Measurement Guidelines.  This list includes Yahoo!, Google, Microsoft and Business.com.  I wanted to take a moment and explore why you should care about this development and what accreditation means for advertisers.

The IAB is a publisher-focused organization that has led the process to develop click measurement guidelines.  The task force is made up of thirty or so companies representing the online advertising community.  Click Forensics has been a member since day one and participated in every step of the process.

There are three main benefits for advertisers and conversely, three concerns advertisers need to keep in mind associated with the entire process.  First, the benefits;

IAB Accreditation Represents a Commitment
The process to become accredited to the IAB guidelines is time consuming and certainly not free.  At Click Forensics, we have first hand knowledge of this and can assure you that any company that takes time and spends the money to become accredited is committed to their customers.  The level of detail the auditors go into is amazing.  Our community is fortunate to have auditors that have demonstrated a deep commitment to both the development of the process and the implementation of the guidelines.

IAB Accreditation Demonstrates Leadership
The IAB established a gating period to allow member companies and others to become accredited to the guidelines.  The companies mentioned above were the first to announce compliance.  This is important because it represents a sense of urgency among these four that enhances the urgency for others.  As an advertiser, you should reward these leaders with business.  They were first out of the gate and in my book that demonstrates leadership.

IAB Accreditation Means Better Quality Traffic
The IAB Guidelines are a lengthy narrative of “best practices” and rules in delivering quality traffic to advertisers.  While it is not intended to be a complete list, it serves as a firm foundation and includes practical steps to help ensure advertisers get what they pay for.  By working with an accredited ad provider, advertisers will be assured that the clicks they are buying have met the guidelines established by the industry.  This is a good thing and an excellent first step.

While we applaud the efforts of the IAB, Media Rating Council and member companies who participated in this process, there are things advertisers need to keep in mind.  There was a great deal of discussion and debate during the nearly three years of meetings it took to develop these guidelines.  In that process, there were a lot of valuable and important items that fell to the floor.  This is a good start, not a perfect process.  Keep in mind the following;

IAB Accreditation is a “Moment in Time” Process
The process for an ad provider to become accredited is a long one.  The auditor is invited in for a pre-assessment then the actual audit begins.  At the end of the process accreditation is awarded.  The problem is there is no mechanism for ongoing compliance.  When we buy gas at the gas station there is a meter that is routinely calibrated to ensure that when we fill our tank with 20 gallons of gasoline, we get 20 gallons.  This approach is not taken nor addressed in the guidelines.  While an annual audit is suggested in the guidelines, it is still important for advertisers to be monitoring their campaigns and holding the ad providers feet to the fire for every click.

IAB Accreditation Does Not Cover Everything
The 27 page Guideline document is quite comprehensive.  Our task force worked hard to ensure that both the guidelines are made clear and that the standard for measurement is defined.  However, when you consider that the dominant constituency in this process was multibillion-dollar ad providers, you might imagine not everything met their liking.  A few examples of chaff that hit the threshing room floor included:

Click ID – Each click should have a unique identifier so investigations can be “apples to apples”
Persistent Cookie – It’s important that ad providers can identify unique visitors to ensure they are billed for only once.
Standards for Investigation – Advertisers deserve to feel confident that they get what they pay for.  By setting an investigation format and agreeing to a timeline, ad providers can build trust with customers.

IAB Accreditation is a Roadmap
There is a Japanese proverb that says, “Beginning is easy and continuing is hard”.  There is truth in this as it relates to the guidelines.  We have begun the process.  We have released guidelines that will make the world of online advertising a better place.  Now we should look to leadership to take the next step and continue what we have begun.  The current guidelines will serve as a roadmap to the future standards.  We need to examine the items removed, listen to the community and think of better ways to ensure advertisers get what they pay for in the future.  The roadmap has been built.  Now we need to move on.

In January of 2006 as Click Forensics was just beginning as a company, I wrote the following challenge to our industry:

“Define standards for what an unwanted click looks like. We believe that there are certain characteristics or attributes that are common to a large percentage of click fraud. We are working with publishers and advertisers to agree on common ground and work together to expose it. Once this is developed it should be published so that the entire community can benefit from it.”

Today, over three years later, we have the cooperation of community leaders, the foundation of technical standards and the desire to continue to improve on what we have built.  I invite you, to join us as we build a future of ongoing growth and improving effectiveness by enhancing the process of online advertising.  I can assure you that both the Click Quality Council and Click Forensics will continue to support the work of the IAB and other industry organizations to work together to make our community a better place.  Let’s not stop with the foundation.

A common question we hear is what our ClickScores mean. In this blog post I want to shed some light on how our scores should be interpreted and present a real-world ad network example.

Whether from an advertiser, publisher or ad network, the Click Forensics scoring engine evaluates every individual click from a paid click stream. Given all the required attributes that describe a paid click, the engine will score each click on a scale from 0 to 1000.

Our ClickScore is a gradient score and, in a nutshell, the higher the score the higher the value of the visitor behind it. Here is a graphical presentation of the overall ClickScore ranges:

To break it down further, a score can be both an indicator of fraudulent or unwanted click activity and a proxy for the likelihood of conversion. Any ClickScore below 100 indicates an invalid click which is typically considered machine-generated traffic or click fraud, while any score above 100 indicates a valid click.

The propensity of conversion increases with a larger ClickScore. A score of 500 denotes a special position in the gradient range as it represents the average odds of conversion based on our training data set of billions of clicks. Scores above 500 indicate a higher than average propensity of conversion. Likewise, scores below 500 denote a lower than average propensity of conversion.

Though our service assigns a score to each individual click, our customers often prefer to look at aggregate scores across a large set of clicks. Depending on customer usage needs, these aggregates can be based on specific sources (e.g. where the traffic is coming from) or on specific attributes (e.g. a particular bid keyword).

For example, our customers like ClickScore distribution charts as a means of traffic quality visualization. In such a chart each individual ClickScore counts towards one of ten buckets. Each bucket represents a score range of 100 points. Below please see a real-world chart from an ad network customer. This chart represents all traffic received from a specific publisher over a the course of a day:

Overall, this publisher can be considered a good traffic source with an average ClickScore of over 500. The majority of the traffic is on the right half of the distribution chart, though there is a significant invalid portion.

For an ad network, such a traffic analysis offers actionable business insights that helps improve traffic acquisition costs from downstream publishers. Further, within a specific traffic source an ad network can identify the invalid traffic referrers to provide input for filtering, routing and pricing decisions. When managing large ad networks with thousands of publishers, detailed downstream traffic information becomes a valuable business asset.

I hope this blog post has helped to shed some light on our ClickScores and also how they can be used by an ad network. If you have any further questions about our products and services please don’t hesitate to contact us.

The New York Times ran a feature article this week on click fraud.  Why you ask?  Because, like spam, click fraud is still a big problem for advertisers. The article pointed out that as the economy tilts downward, advertisers cannot afford to waste dollars. This is a good news, bad news scenario for online advertising.

The good news is that online advertising is highly measurable.  Large advertisers that traditionally have been offline are now shifting dollars online.  This fact has contributed to online advertising continuing to grow as traditional media is in decline.

The bad news however, is that this window of opportunity is narrow.  The online advertising community must embrace measurability and enhance trust to gain share of spend from the big guys. 

There was a significant event this week that helped in that effort.  The Interactive Advertising Bureau (IAB) released from draft the Click Measurement Guidelines.  This document, three years in the making, is a great start for our community to come together around standards and enhance trust. Dozens of ad providers are busily working with third party audit firms to become accredited to the new guidelines.  Advertisers will have a way to gauge the level of commitment from ad provides when this list is made public.

Click Forensics was proud to represent advertisers in this process.  In fact, we were the only traffic quality management firm to participate and were quoted in the press release from the IAB.  Many thanks are in order for the 38 members of the working group for a job well done.

Now, we find ourselves at the beginning.  An opportunity exists to build on the foundation laid by the IAB member companies.  Click fraud is going to be a problem for a long time to come.  Progress is being made.  But in order to re-accelerate the growth of online advertising we need more than standards.  We need a community effort to work together to ensure advertisers have confidence that they get what they pay for.  Articles raise awareness, documents create a process and awareness builds urgency.  But ultimately it will take the effort of everyone in the community to get to the day where trust is commonplace and online advertising becomes the marvelous, measurable media it can be.  We look forward to continuing our efforts toward that goal.

Today the Click Fraud Index for Q1 2009 was released, and the startling news would appear to be that the click fraud rate in Q1 dropped to 13.8% from over 17% a quarter ago.  But there are several plausible explanations for the sharp drop in click fraud.  The real news was in the types of fraud that were identified, and the likely targets of these new attacks.

So why the drop-off?  Several factors likely contributed.  First, the Q4 fraud rate was unusually high, the highest ever in the history of publishing the click fraud index.  Due to the huge amount of online spending during the holiday season and the eroding economic climate, there was a sort of “perfect storm” for fraudulent activity.  In Q1, by contrast, there was a drop-off in online ad spending — Google reported their first-ever quarterly revenue decline — and more importantly, a decrease in the average cost-per-click (the number of paid clicks still increased by 17%, even though total revenue was down).  Lower CPCs means less reward for fraudsters.

Maybe the most important contributor to the reduced click fraud rate, though, was the heightened awareness of bots, worms, and other forms of malware created by the Conficker reporting (anyone see “60 Minutes?”).  It would appear that the tier 1 ad providers and ad networks did a much better job of mitigating fraudulent activity in Q1 than in previous quarters.  We can only hope this is a trend that continues.

But the more interesting trend uncovered in the Q1 data were the new types of fraud and the new targets of click fraud.  The data showed several examples of malicious scripts (JavaScript) designed to perpetrate click fraud.  When a visitor lands on a site these scripts execute by opening a zero iframe or zero-pixel window and clicking on paid ads.  The site visitor never sees these hidden frames and never visits the advertiser’s site.  But the advertiser pays for the click, and the site owner reaps the commission for the paid click.  Because the clicks are generated by a real browser with a valid IP address on a real web site with no suspicious repeat clicking patterns, this type of fraud is very difficult to discover for the average advertiser or unsophisticated ad network.  (No, we can’t tell you how we find it, but we do.)

The bottom line is that the click fraud rate was down in Q1, but click fraud schemes continue to get more sophisticated.  As tier 1 ad networks and ad providers like Yahoo! and Google continue to increase their efforts and effectiveness, the fraudsters will migrate elsewhere.  Tier 2 ad networks must focus on traffic quality initiatives in order to protect their advertisers, and themselves.

For our advertiser customers we are introducing an new integration option called the Click Forensics Redirect Service (CFRS). It’s an alternative approach to sharing click stream data with us and will often simplify the initial on-boarding process for new customers.

Instead of uploading web server log files, which often requires help from the IT department, customers only need to update their campaign settings to use CFRS. This change will send their click stream data with all necessary data fields to our Click Forensics scoring service.

Here is a conceptual overview of how CFRS integrates with paid search campaigns:

CFRS operates as an interstitial redirect page. It injects itself between the paid click and the landing page, thereby observing all click stream data. To enable it, customers update their destination landing page URLs to use a new format that will transparently invoke CFRS. This change will not impact the experience of end users visiting paid search advertisements.

From the initial customer feedback, we have learned that CFRS was an elegant alternative to sharing web server log file data and eased the initial on-boarding process. If you have been contemplating to improve your search marketing budget by removing irrelevant keywords and invalid clicks, please make sure to learn more about our offerings for advertisers.