Skip to content

FRM Part I · FRM Exam Part I · Machine-Learning Methods

A bank has transaction records for 200,000 corporate clients with no predefined categories. The risk team applies k-means to group clients with similar transaction patterns and then inspects each group for unusual behavior. Which statement best describes this approach?

The approach is unsupervised learning. K-means groups clients using only their features, with no known target labels. Choosing k is a hyperparameter setting, not a label, and nothing involves reward-based sequential decisions, so supervised and reinforcement learning descriptions do not fit.

  1. AIt is unsupervised learning, because the algorithm finds structure in unlabeled dataCorrect
  2. BIt is supervised learning, because the number of clusters k is specified in advance
  3. CIt is reinforcement learning, because the team reviews the groups and adjusts them
  4. DIt is supervised classification, because each client is assigned to one group

Explanation

Clustering uses only input features and no target labels, so it is unsupervised learning. Specifying k is a hyperparameter choice and does not create labels. Assigning clients to groups is not classification against known labels, and no reward-driven sequential decisions occur.

Did you get it right without looking?

One question tells you little. A timed set on Machine-Learning Methods shows your real accuracy, how long you take and where you lose marks.

Practise Machine-Learning MethodsFree diagnostic mock

More Machine-Learning Methods questions