Skip to content

ACCA Strategic Professional · Advanced Performance Management · Data science and analytics

Orrin Bank has built a model using customer data. The model achieves very high accuracy on the data used to build it but performs poorly when applied to new customers. Which problem does this most likely indicate?

The problem is most likely overfitting. The model has learned random noise and quirks of the training data, so it scores highly there but generalises badly to new customers. Underfitting would instead produce weak results on both the training data and new data.

  1. AUnderfitting, because the model is too simple to capture patterns
  2. BOverfitting, because the model has learned noise specific to the training dataCorrect
  3. CData latency, because the data was captured too slowly
  4. DSelection of an unsupervised method instead of a supervised method

Explanation

A model that excels on its training data but fails on unseen data has captured noise rather than general patterns, which is overfitting. Underfitting would show poor performance on both training and new data. The scenario gives no evidence of latency or of the method type.

Did you get it right without looking?

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

Practise Data science and analyticsFree diagnostic mock

More Data science and analytics questions