4predictivePredictive behavioral targeting uses a linking of surveys and measurement data to open up the entire spectrum for behavioral targeting. It learns from user behavior combined with surveys or other third party data in real time. Machine-learning algorithms are put to work in order to provide ad servers with precise profile information for the whole inventory. The technology used is the same as in research on artificial intelligence and robotics.

In a nutshell, the methodology encompasses three steps:

  1. Cookies are saved on the computers of all users of a portal or marketing network. These cookies indicate how often the users have visited certain websites (measurement).
  2. A random sample of users is polled on their demographics, interests and lifestyle (surveys).
  3. This information is overlaid - online and in real time - onto the entirety of the user group (projection).

This process provides a complete targeting profile, containing both product interests on the basis of visited online content as well as indications of demographics, interests and lifestyle. Survey data is projected onto the entirety of users by forming "statistical twins": Users without survey data "inherit" the missing survey data from those surveyed users whose measured surfing behavior most closely resembles their own.

Predictive behavioral targeting is made possible through a technological system that analyzes and enhances user data online and in real time. Blind gifs are used to count the number of page hits per cookie and content page code. Additionally, random users are invited at certain intervals to take part in on-site surveys, providing information on the user's demographics, interests and lifestyle. This polling data is then overlaid onto the measurement data, allowing for a profile comparison. The profile will then be delivered to portal operators and their ad servers, who can then send out ads to the previously defined target group.

Research has shown that only 15% of users ever click on online advertisements. But does that necessarily mean an advertisement didn‘t leave an impression? The goal of successful online marketing shouldn‘t be getting consumers to click on something, but rather to establish a brand in consumers‘ heads. Achieving click rates has so far been the main goal of digital marketing, but predictive behavioral targeting is more important than click rates.

What the digital marketing space really needs is intelligent target group management and metrics which can measure branding effects. The impression made on users is what needs to be measured, just as if it were TV or billboard advertising. Digital advertising needs the right dose across all channels with great reach and real time adjustments.

The goal of predictive targeting is brand performance. This means reaching highly specific target groups in a very effective manner with the right amount of advertising to establish a branding message. Brand engagement plays an important role as well, encouraging an important segment of customers or prospects to engage in a dialogue with the brand.

Click rates are accurate and easily measured, but even in classical media planning nothing is 100% accurate and traditional advertising still brings excellent results. Maybe digital marketers need to accept the fact that marketing is not 100% measurable, ever, in order for digital advertising to grow up. The results of research by IP Deutschland and Zed digital showed that the predictive targeting reached the target group 168% more effectively than traditional targeting.

nugg.ad offers target group specific online advertising solutions in order to minimize wasted advertising and continuously optimize advertising effectiveness. The technology is capable of delivering brand metrics for scientific measurement of branding effectiveness. The data is, in turn, interpreted into concrete improvement suggestions. This type of targeting delivers higher levels of precision compared to advertising placed by selected online channels.

The nugg.ad Open Targeting Platform offers unique networking opportunities to agencies, publishers and data providers to conduct targeting campaigns spanning different publishers. Publishers themselves can work with us to tap new revenue streams for their advertising.



nugg.ad predictive behavioral targeting is based on various discrete data sources. For real-time predictions data based on a given user’s surfing behavior is used, mixed together in the measurement process with survey data and optionally external sources (such as socio-demographics and product interests). The delivery of online advertising is controlled by algorithms which draw on statistical models to accurately appoint an optimal advertising placement.

nugg.ad allows you to select socio-demographic data and product interests for your campaign, right down to individual target group definitions, if desired. Another option is using nugg.ad hotspots to address pre-defined target groups.

What do you think? Should digital marketers rethink in terms of the importance of click rates, and does predictive behavioral targeting sound promising?

By Anjum Siddiqi