Expand my Community achievements bar.

Applications for the 2024 Adobe Target Community Mentorship Program are open! Click to the right to learn more about participating as either an Aspirant, to professionally level up with a new Certification, or as a Mentor, to share your Adobe Target expertise and inspire through your leadership! Submit your application today.
SOLVED

Remove parameters from mbox

Avatar

Level 2

Hello, 
We lead a test on target, to discover how does mbox parameters works : 
we would like to remove those parameters from our global mbox and avoid clutter, 

Do we have to create another mbox ?

Is there any other solution to discard those tests parameters ? 

 

Julien BIJOUX, 

1 Accepted Solution

Avatar

Correct answer by
Level 10

Hi Julien, 

Is the problem solved ?. If not, Please let us know so that we can further help you with the same.

Thanks & Regards

Parit Mittal

View solution in original post

3 Replies

Avatar

Employee Advisor

Julien,

So you added parameters to your global mbox and now you want to remove them?  How did you add them--via the DTM UI or with your own custom code?  I would just  remove the changes you made to add them in the first place.  You don't need to create another mbox.

Avatar

Correct answer by
Level 10

Hi Julien, 

Is the problem solved ?. If not, Please let us know so that we can further help you with the same.

Thanks & Regards

Parit Mittal

Avatar

Level 2

Hello the problem is almost solved,

I realized there are missing points on my initial question:

First we wanted to leverage the power of ML  Random Forrest algorithm in our Adobe Target

experience.

Therefore we wanted to use some insights we learned from our clients throught DMPs and find out

the discriminant values in thoses variables. But - using Global Mbox to fire up the experience we faced of

a problem :

Most discriminant variables were screen size, browser , or mobile  / desktop information  .

This was due to the fact that our current experience was far more efficient on mobile than on desktop,

This lead us to 3 conclusions :

- Machine learning was learning on wrong value

- Machine learning was eaysilly prone to platform impact

- Never setup a ML Experience without having the first tried an A/B Test
and went through analysis

So how did we solve the problem ? Easier than we thought but a little bit tricky also :

  1. Deploy a custom mbox with DTM (or any TMS)
  2. Send "choosen" parameters to feed the ML algorithm
  3. Refine the goal on which ML is learning from
    More precise the goal is, more precise the result is !
    In many way thinking that visiting page X should be  the result
    is not precise enougth !


By the way the part on Deploying custom mbox through DTM is de facto not

the easiest path to setup  an industrialized means of production,