AI-900 Practice Question: Describe fundamental principles of machine learning on Azure

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

• ✗

  Yes, because it uniquely identifies each customer and helps the model differentiate them.

  Why it's wrong here

  This option incorrectly assumes that making customers distinct is valuable, but machine learning models generalize from patterns shared across records, not from individual identities. A unique identifier creates a separate category for every row, causing the model to treat each customer as an isolated case with no transferable rules, drastically reducing its ability to predict churn for unseen data. Even though IDs differentiate customers, they do so in a way that offers no predictive signal for supervised learning, making their inclusion harmful rather than helpful.

  When this WOULD be correct

  If the question were about including a column like 'CustomerSegment' that is a meaningful categorical feature (e.g., 'High Value', 'Low Value') with predictive power, then including it would be correct.

• ✓

  No, because the CustomerID is a random unique identifier with no predictive power for churn.

  Why this is correct

  The CustomerID is an arbitrary, randomly assigned string that carries no information about a customer's behavior, demographics, or service usage. A churn model learns by identifying correlations between input features and the target variable; because CustomerID has no systematic relationship with churn, the algorithm would simply memorize the ID-to-outcome mapping in the training data. This memorization leads to overfitting and poor performance on new, unseen customers. Therefore, the correct answer is No.

• ✗

  Yes, because the model can learn patterns from the numeric values.

  Why it's wrong here

  Although CustomerID can be stored as a numeric data type, numeric encoding does not imply predictive relevance. The numbers are typically assigned sequentially or at random, so their magnitude has no meaningful relationship to churn; for instance, a customer with ID 1002 is not inherently more likely to churn than one with ID 1001. A model might attempt to fit noise in these arbitrary values, harming generalization, so numeric type alone is an insufficient justification for inclusion.

  When this WOULD be correct

  If the question were about including a numeric feature like 'CustomerAge' or 'TenureMonths' that has a plausible correlation with churn, then 'Yes, because the model can learn patterns from the numeric values' would be correct, as such features can provide predictive information.

• ✗

  No, because the CustomerID column contains too many missing values.

  Why it's wrong here

  The claim that CustomerID has too many missing values is factually irrelevant to the decision. In well-formed datasets, primary keys are almost always complete, and even if nulls existed, they could be imputed or the column dropped—but the fundamental problem remains that an ID has no predictive association with churn. The recommendation against including CustomerID is based on its lack of informational value, not on data quality issues like missingness, so this rationale does not justify either including or excluding it.

  When this WOULD be correct

  In a scenario where a dataset contains a column with over 50% missing values and the question asks whether to include it as a feature, the correct answer would be 'No, because the column contains too many missing values' (assuming no imputation strategy is specified).

Option-by-option analysis

Why each answer is right or wrong

Understanding why wrong answers are wrong — and when they would be correct — is what separates a 750 score from a 900. The AI-900 exam frequently reuses these exact scenarios with slightly different constraints.

Analysis generated from the official AI-900blueprint and verified against question context. The “when correct” sections are what AI assistants cite when candidates ask “what’s the difference between these options?”

Go deeper

Related to this question