Skip to content

FRM Part I · FRM Exam Part I · Machine Learning and Prediction

An analyst at a risk consultancy wants to group 400 corporate borrowers into segments based on leverage, interest coverage and asset volatility, with no pre-labelled default outcomes. Which description best characterizes the K-means algorithm she intends to use?

K-means is an unsupervised method that repeatedly assigns each observation to its nearest centroid and recomputes the centroids as cluster means until assignments stop changing. It needs K specified beforehand and uses no labelled outcomes, unlike supervised methods or hierarchical clustering.

  1. AA supervised method that fits a labelled default indicator to the three features
  2. BAn unsupervised method that assigns each observation to the nearest of K centroids and then recomputes the centroids until assignments stabilizeCorrect
  3. CAn unsupervised method that builds a tree of nested clusters without needing to specify K in advance
  4. DA supervised method that minimizes prediction error on a held-out validation sample

Explanation

K-means is unsupervised: it assigns each point to its nearest centroid, recomputes centroids as cluster means, and repeats until assignments no longer change. Building a nested tree describes hierarchical clustering, not K-means. No labels are used.

Did you get it right without looking?

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

Practise Machine Learning and PredictionFree diagnostic mock

More Machine Learning and Prediction questions