QUESTION: 96 Exam Topic: Implement AI predictions in Customer Insights

Your organization’s IT team wants to use the out-of-the-box customer lifetime value (CLV) machine learning (ML) capabilities that come with Microsoft Dynamics 365 Customer Insights. The team has some concerns about the suitability of their data.
You need to provide recommendations for data characteristics that will improve the accuracy of the CLV model.
Which two recommendations should you provide? Each correct answer presents a complete solution.

NOTE: Each correct selection is worth one point.

There should be at least two to three transactions per customer ID preferably across multiple dates.
At least 90 percent of all fields required for the model should contain data.
There should be at least 100,000 unique customers to perform the CLV model.
There should preferably be two to three years of transactional data to predict CLV for one year.

Answer(s): A,D

Explanation:

A: Ideally, at least two to three transactions per customer ID, preferably across multiple dates.

D: At least one year of transaction history, preferably two to three years.

Incorrect:
Not B: Less than 20% missing values in required fields
Not C: At least 100 unique customers, preferably more than 10,000 customers

Reference:

https://learn.microsoft.com/en-us/dynamics365/customer-insights/predict-customer-lifetime-value

Reveal Solution Next Question

QUESTION: 97 Exam Topic: Implement AI predictions in Customer Insights

Your Microsoft Dynamics 365 Customer Insights environment has only one segment. This segment includes customers who have purchased a type of product in the past.

The marketing team wants to send product samples to other customers who are likely to purchase that same type of product. The team asks you to make recommendations for configuring a “find similar customers” model.

You need to recommend a solution that meets the following requirements:
-The expansion segment model needs to be as accurate as possible.
-The marketing team must be prevented from sending samples to customers who have already purchased that product.

What should you recommend?

Set the maximum number of members to a value no greater than 40 percent of all customers.
Include members of the source segment in addition to customers with similar attributes.
Exclude fields with a cardinality of less than two or more than 30 distinct values.
Select all fields except for alternate id from the source segment for the model.

Answer(s): C

Explanation:

Fields that can significantly reduce the model performance are automatically excluded:

Fields with the following data types: StringType, BooleanType, CharType, LongType, IntType, DoubleType, FloatType, ShortType
Fields with a cardinality (the number of elements in a field) of less than 2 or more than 30

Incorrect:
Not B: The source segment should be excluded.
Include customers in your source segment by selecting the Include members from source segment in addition to customers with similar attributes checkbox.

Reference:

https://learn.microsoft.com/en-us/dynamics365/customer-insights/find-similar-customer-segments

Reveal Solution Next Question

QUESTION: 98 Exam Topic: Implement AI predictions in Customer Insights

You are configuring Microsoft Dynamics 365 Customer Insights for a company that sells subscription packages to individuals for online music lessons. The Chief Marketing Officer (CMO) wants to implement an out-of-the-box churn prediction model for customers.

You need to tell the CMO what information is required to successfully configure a prediction model for the company's lesson packages.

Which two pieces of information must be provided by the CMO? Each correct answer presents a complete solution.

NOTE: Each selection is worth one point.

Subscription amount
Unique product id
Transaction date
Subscription start date

Answer(s): C,D

Explanation:

Predict subscription churn

Prerequisites
* At least Contributor permissions.
* At least 10 customer profiles, preferably more than 1,000 unique customers.
* Customer Identifier, a unique identifier to match subscriptions to your customers.
Subscription data for at least double the selected time window. Preferably, two to three years of subscription data
Subscription history must include:
Subscription ID: Unique identifier of a subscription.
Subscription End Date: Date the subscription expires for the customer.
(D) Subscription Start Date: Date the subscription starts for the customer.
(C) Transaction Date: Date a subscription change happened. For example, a customer buying or canceling a subscription.
Etc.

Reference:

https://learn.microsoft.com/en-us/dynamics365/customer-insights/predict-subscription-churn

Reveal Solution Next Question

QUESTION: 99 Exam Topic: Implement AI predictions in Customer Insights

Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution.

After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear in the review screen.

You are responsible for creating segments for your company’s marketing team using Microsoft Dynamics 365 Customer Insights.

Your Chief Marketing Officer (CMO) wants to run a re-engagement campaign for customers that have a high probability of no longer purchasing your organization’s products in the next three months.

The CMO asks you to use Dynamics 365 Customer Insights to generate a segment of customers that would meet this requirement.

Solution:
1. Generate an attribute-based segment suggestion using a measure for “number of purchases in the past three months,” and “loyalty customers” as an assessment attribute.
2. On the Suggestions page, create a segment on the suggestion tile.

Does this meet the goal?

Answer(s): B

Explanation:

Instead: Solution:
1. Generate a Transactional churn prediction for the next three months.
2. On the results page, review the model results to identify the characteristics of the highest “Likelihood to churn” group.
3. Create a segment from the results page using the ChurnScore field and a Greater than operator for the lower bounds value of the group you identified.

Note: Transactional churn prediction helps predict if a customer will no longer purchase your products or services in a given time window.

You must have business knowledge to understand what churn means for your business. We support time-based churn definitions, meaning a customer is considered to have churned after a period of no purchases.

Note 2:

In the output entity for this model, ChurnScore shows the predicted probability of churn and IsChurn is a binary label based on ChurnScore with 0.5 threshold.

Reference:

https://learn.microsoft.com/en-us/dynamics365/customer-insights/predict-transactional-churn

Reveal Solution Next Question

Free MB-260 Exam Braindumps (page: 15)

QUESTION: 96 Exam Topic: Implement AI predictions in Customer Insights

Explanation:

Reference:

QUESTION: 97 Exam Topic: Implement AI predictions in Customer Insights

Explanation:

Reference:

QUESTION: 98 Exam Topic: Implement AI predictions in Customer Insights

Explanation:

Reference:

QUESTION: 99 Exam Topic: Implement AI predictions in Customer Insights

Explanation:

Reference: