Expert's tips / 26 February 2019
Our clients sometimes ask us to advise them on the optimal use of predictive scores as part of their Direct Marketing campaigns. They understood that scores are valuable only if they are part of activation campaigns and / or Marketing Automation.
First, remember that behind these scores is an intention (sometimes still latent) of the consumer to adopt a commercial behavior: the acceptance of an offer, a (lack of) interest for a product or a category of products, a departure of the Company as a customer or subscriber …
Some customers release “high” scores, others “weak” according to discriminant characteristics that the modeling will have determined and weighted. In “output”, Data Scientists or Predictive Marketing software deliver a “scored” database that will often be re-ranked in descending order. In the case of software, this database will be organized by “score classes” to facilitate upstream work.
It is precisely this scored database that the marketer will use to get the most out of his Direct Marketing campaigns. The predictive scores will allow to be more selective in the choice of profiles and therefore to increase the conversion while reducing the costs of Direct Marketing.
Then comes the question: Do I pick 10%, 20%, the top of the basket or the 30% of the most “inclined to” profiles for the campaign?
The answer is twofold and dictated by
It’s your turn !
Managing Director & Partner at Inbox Belgium