AIF-C01 Fundamentals of AI and ML Practice Question

A retail bank has millions of unlabeled customer transaction records and wants to discover natural groupings of spending behavior without defining any categories in advance. The data science team plans to use an unsupervised learning approach. Which technique is designed for this goal?

⚠ Common exam trap

The trap here is reaching for a familiar supervised algorithm such as regression or a classifier even though the data has no labels and no target to predict.

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

✓

K-means clustering, which partitions records into groups so that members of a group are more similar to each other.

The bank has no predefined categories and wants to uncover structure in unlabeled data, which is the defining use case for unsupervised learning. K-means clustering groups similar records together so the team can inspect and name the resulting segments afterward, turning raw transaction behavior into actionable customer groupings.

Answer analysis

Option-by-option breakdown

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

✗
Linear regression, which models the relationship between a continuous target and one or more input features.
Why it's wrong here
Linear regression is a supervised technique that requires a known continuous target value for each record. The bank's transaction data has no predefined outcome to predict, and spending behavior groupings are not continuous quantities. Applying regression here would force the team to invent a target, which defeats the purpose of discovering structure in unlabeled data.
✗
Logistic regression, which estimates the probability that a record belongs to a particular class.
Why it's wrong here
Logistic regression is supervised classification and needs labeled examples of each class to learn decision boundaries. The bank has no labels indicating which spending group a customer belongs to, so there is nothing for logistic regression to fit. It could only be used after clusters were defined and labeled, which is the opposite of the exploratory goal described.
✗
A decision tree classifier, which splits data using feature thresholds to predict a labeled category.
Why it's wrong here
A decision tree classifier is supervised and requires a labeled target column to determine which splits reduce impurity. With only unlabeled transaction records, the algorithm has no target to optimize and cannot build meaningful splits. The bank's objective is to reveal structure rather than predict a known category, so a clustering method is appropriate instead.
✓
K-means clustering, which partitions records into groups so that members of a group are more similar to each other.
Why this is correct
K-means is an unsupervised algorithm that groups unlabeled records into a chosen number of clusters based on feature similarity. It directly matches the bank's goal of discovering natural spending-behavior segments without predefined categories. The team can then profile each cluster, for example frequent travelers versus everyday local spenders, to inform marketing or risk decisions.

Go deeper

AIF-C01 Fundamentals of AI and ML Practice Question

Why each option matters

Option-by-option breakdown

Related to this question