Skip to content

IAI Actuarial Core Principles · Risk Modelling and Survival Analysis · Elementary principles of machine learning

A health insurer groups 50,000 customers into segments using only age, income and claim frequency, with no predefined segment labels. Which statement best describes this task?

It is unsupervised learning. No target or predefined segment labels exist, so the algorithm looks for structure among the features themselves, as in clustering. Supervised methods would require known labels or an outcome variable to predict.

  1. ASupervised regression, since claim frequency is numerical
  2. BSupervised classification, since segments are categories
  3. CUnsupervised learning, since no target labels are suppliedCorrect
  4. DReinforcement learning, since the insurer rewards good segments
  5. Semi-supervised learning, since income is partly labelled

Explanation

Segmentation with no pre-existing labels seeks structure in the inputs alone, which is unsupervised learning (clustering). Claim frequency is used here as a feature, not as a target to predict. Classification would need labelled segments.

Did you get it right without looking?

One question tells you little. A timed set on Elementary principles of machine learning shows your real accuracy, how long you take and where you lose marks.

Practise Elementary principles of machine learningFree diagnostic mock

More Elementary principles of machine learning questions