MB-910 Describe Dynamics 365 Customer Insights Practice Question
You are a customer data analyst at a financial services company. The company uses Dynamics 365 Customer Insights to manage customer data. Recently, the marketing team created a segment called 'High Propensity to Buy' using a predictive model built in Customer Insights. The segment is used in a real-time marketing campaign in Dynamics 365 Marketing. The campaign has been running for a week, but the marketing team reports that the segment size seems to be decreasing each day, and they are concerned that customers are being incorrectly removed. Upon investigation, you find that the predictive model is retrained nightly based on the latest transaction data. What is the most likely cause of the shrinking segment?
⚠ Common exam trap
Test-takers frequently assume the predictive model is static or that segment membership is fixed once created, rather than understanding that nightly retraining dynamically recalculates scores and can shrink segments as customer behavior changes.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
The predictive model's propensity scores are being recalculated nightly, and some customers no longer meet the threshold due to recent data
The predictive model in Dynamics 365 Customer Insights is retrained nightly using the latest transaction data. This retraining recalculates propensity scores for all customers. As new transaction data is ingested, some customers' scores may drop below the threshold defined for the 'High Propensity to Buy' segment, causing them to be automatically removed from the segment. This daily recalibration is the most likely reason for the shrinking segment size.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
The marketing team is manually removing customers from the segment based on campaign feedback
Why it's wrong here
Manual removal would be visible in logs and is not automatic.
- ✗
The predictive model is failing to calculate scores for all customers, resulting in fewer qualified customers
Why it's wrong here
A failing model would likely produce errors, not systematic decreases.
- ✓
The predictive model's propensity scores are being recalculated nightly, and some customers no longer meet the threshold due to recent data
Why this is correct
Daily retraining can change scores, causing dynamic segment membership to fluctuate.
- ✗
The data source for transactions is being refreshed, causing some customer profiles to be temporarily unavailable
Why it's wrong here
Profiles are not removed during refresh; they are updated.
Go deeper
Related to this question
About these practice questions
Courseiva writes every MB-910 question from scratch — 941 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This MB-910 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the MB-910 exam.