![splash-1](/wp-content/themes/lumen/images/splash/splash-1.png)
![splash-2](/wp-content/themes/lumen/images/splash/splash-2.png)
![splash-3](/wp-content/themes/lumen/images/splash/splash-3.png)
![splash-4](/wp-content/themes/lumen/images/splash/splash-4.png)
![splash-5](/wp-content/themes/lumen/images/splash/splash-5.png)
![splash-6](/wp-content/themes/lumen/images/splash/splash-6.png)
![splash-7](/wp-content/themes/lumen/images/splash/splash-7.png)
Lumen attention prediction model
Combining placement and attention data
![](https://lumen-research.com/wp-content/uploads/2021/05/Internet-scaled.jpg)
Lumen attention panel gives us:
- Placement data: What ads could be seen (what was viewable, in what location and for how long, etc.)
- Attention data: What ads people did, in fact, see, and for how long
Predicting attention from placement data
![](https://lumen-research.com/wp-content/uploads/2021/05/Algorithm-2-scaled.jpg)
Placement and attention data from the eye tracking panel is used to power a predictive model of attention
Estimates likely levels of attention based on a number of placement characteristics
Attention to ad predicted every 100ms of exposure
Placement data included in model
![](https://lumen-research.com/wp-content/uploads/2021/05/Algorithm-.jpg)