Skip to content

ACCA Strategic Professional · Strategic Business Leader · Machine learning, AI and robotics

Brindle Retail has no predefined customer categories. Its data team applies an algorithm to purchase histories so that it finds natural groupings of shoppers, and marketing will then decide how to treat each group. Which approach and implication best fit this case?

The case describes unsupervised clustering. The algorithm discovers natural customer groups from unlabelled purchase data, so management must interpret the segments and judge whether they are meaningful before acting. Supervised classification would require predefined labelled categories, which Brindle does not have.

  1. ASupervised classification; the outcome categories were set by management beforehand
  2. BReinforcement learning; the algorithm is rewarded for each sale made
  3. CUnsupervised clustering; the groups are discovered from the data and need human interpretation before useCorrect
  4. DNatural language processing; the algorithm reads customer reviews to infer sentiment

Explanation

No labels or predefined categories exist, so the algorithm finds structure itself, which is unsupervised clustering. The business must interpret and validate the segments before acting on them. Supervised classification would need labelled training examples, which are absent here.

Did you get it right without looking?

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

Practise Machine learning, AI and roboticsFree diagnostic mock

More Machine learning, AI and robotics questions