Skip to content

CMA Intermediate · Financial Management and Business Data Analytics · Data Analysis and Modelling

A bank wants to group its customers into segments based on spending behaviour without any pre-labelled outcome. Which analytical technique is most appropriate?

Clustering, an unsupervised learning method, is appropriate. It groups customers by similarity in spending behaviour without needing a predefined label or target. Regression and classification need labelled outcomes, and time-series forecasting predicts future values rather than forming segments.

  1. AClustering, an unsupervised learning methodCorrect
  2. BLinear regression, a supervised learning method
  3. CClassification using labelled default data
  4. DTime-series forecasting of monthly deposits

Explanation

Grouping records by similarity when no outcome label exists is the task of clustering, an unsupervised method. Regression and classification need a labelled target variable. Time-series forecasting predicts future values over time, not segments.

Did you get it right without looking?

One question tells you little. A timed set on Data Analysis and Modelling shows your real accuracy, how long you take and where you lose marks.

Practise Data Analysis and ModellingFree diagnostic mock

More Data Analysis and Modelling questions