Skip to content

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

A general insurer wants to predict the claim amount (in rupees) for each motor policy from rating factors such as vehicle age, engine capacity and city. Which description of the task is correct?

This is supervised learning with a continuous response, so it is a regression problem. Each training policy has an observed claim amount as the label, and the aim is to predict a numerical value. Classification would need a categorical target, such as whether a claim occurs.

  1. ASupervised learning with a continuous response, which is a regression problemCorrect
  2. BSupervised learning with a categorical response, which is a classification problem
  3. CUnsupervised learning, because no policy is excluded from the data
  4. DUnsupervised clustering, because rating factors are used as inputs
  5. Reinforcement learning, because claim amounts arrive over time

Explanation

The response, claim amount, is numerical and observed for each training policy, so the labelled data make this supervised learning. A continuous response means regression. Classification would apply only if the target were a category such as claim or no claim.

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