Learn the correct approach for a Salesforce consultant to model customer value by aggregating individual revenue amounts over 2 years. Understand how to properly set up the outcome variable for the Einstein Discovery model.
Table of Contents
Question
To model customer value, a consultant decided to aggregate the amount ($) individual customers spent over a 2-year span.
With reference to the outcome variable, which action should the consultant take?
A. Create five bins of revenues, ranging from Very High Value, High Value, Average Value, Low Value, and Very Low Value in data prep.
B. Create five bins of revenues, ranging from Very High Value, High Value, Average Value, Low Value, and Very Low Value in dataflow.
C. Select to minimize the outcome variable.
D. Select the option: Are you expecting a whole number greater than or equal to 0?
Answer
D. Select the option: Are you expecting a whole number greater than or equal to 0?
Explanation
When modeling customer value, the consultant has aggregated the dollar amount each customer spent over a 2-year period. This results in a numeric outcome variable representing the total revenue per customer.
In Einstein Discovery, when defining a numeric outcome variable, you need to specify whether you expect the values to be whole numbers greater than or equal to zero. This is important because it impacts the model and evaluation metrics used.
Creating bins or buckets of the outcome variable, like Very High Value down to Very Low Value, is not the correct approach here. Binning the numeric outcome variable into categories would turn it into a categorical target, which is not the goal. The consultant wants to predict the actual revenue amount per customer, not a revenue range or category.
Additionally, minimizing the outcome variable is not relevant in this scenario. That would be done if the goal was to reduce or optimize the numeric outcome, which is not the case for modeling customer value.
Therefore, the consultant should keep the outcome as a numeric variable and select the option specifying that the values are expected to be whole numbers greater than or equal to zero, since customer revenue amounts are non-negative integers.
By properly defining the outcome variable, the consultant ensures that Einstein Discovery builds an appropriate model to predict the revenue amount per customer based on the aggregated data.
Salesforce Certified Tableau CRM and Einstein Discovery Consultant certification exam assessment practice question and answer (Q&A) dump including multiple choice questions (MCQ) and objective type questions, with detail explanation and reference available free, helpful to pass the Salesforce Certified Tableau CRM and Einstein Discovery Consultant exam and earn Salesforce Certified Tableau CRM and Einstein Discovery Consultant certification.