2) Configure and Train a Prescriptive Exhaustive Model

This Blog entry is from the Exhaustive Basics section in Learn Exhaustive.

One of the interesting and unique features in Exhaustive is the ability for models to be recalled where certain variables are randomised to observe the effect it has on the score at recall.  Fluttering certain variables in this way can facilitate experimentation in real-time to prescribe an optimal solution to a problem.

Creating a prescription model is exactly the same as creating other models in Exhaustive, with the additional step being the specification of variables that are to be used as prescription variables.

In this Blog entry, repeat the steps as detailed in the previous Blog entry, with the following file but stop short at clicking the Start button:



This is structure in the same manner as the FraudRisk.csv file, although there is a field called Response Elevation (i.e. bid) for which optimisation is sought.  Specifying the variable as being Prescriptive instructs exhaustive to simulate the variable on model recall, rather than rely on what has been passed (if indeed such a value exists at the time of recall):


In this example, as it is thought that geography plays an important part in AdTech, fix the Latitude and Longitude fields such that these variables will be in an Exhaustive trial as a minimum:


Click on the Start button to begin the training: