On Friday, Click Forensics announced a new service they are offering that helps predict high conversions. Click Forensics is known for tracking the click fraud rate in the search industry. This new tool promises to “allow online ad networks, publishers and advertisers to identify traffic that’s more likely to convert into sales.”
The platform includes the following features:
Click Forensics Site Score – sources of traffic are tagged with individual Click Forensics Site Scores that rank visitors based on their propensity to convert. This allows ad networks to more effectively filter and route traffic for highest monetization and provide the best ROI for online advertisers.Adaptive Intelligence – to accommodate varying traffic profiles among different ad networks, advertisers, and publishers, the new engine provides the capability to adjust rules and thresholds to produce traffic quality scores that better reflect propensity to convert for each specific client. For example, an ad network that caters to retailers in Asia might have very different traffic patterns than a B2B ad network in North America.Machine Learning – the traffic scoring engine also employs new machine learning capabilities that allow it to adapt and tune itself in real-time to detect new sources of good and bad traffic as they emerge. Filtering decisions can be made instantly based on traffic quality thresholds set by clients.Enhanced Anomaly Detection – more granular click anomaly detection features can distinguish new complex click types – machine or human – even from the same computer. This includes increasingly popular malicious Javascript programs that execute upon a page view or site visit. In addition, volume and spike anomalies can be more easily identified to protect from stealth attacks, such as those resulting from botnet activation.
A WebmasterWorld thread has members of the search marketing community who are very skeptical about the tool. One advertiser said:
Like with any tool in this market, you need to use it with wisdom and not go by it blindly.
Forum discussion at WebmasterWorld.
