Skip to content

CS Professional · Artificial Intelligence, Data Analytics and Cyber Security - Laws and Practice · Artificial Intelligence - Introduction and Basics

An Indian e-commerce company finds that its recommendation model performs very well on the data used to build it but poorly on fresh customer data, because it has memorised noise in the training set. What is this problem called?

The problem is overfitting. The model has memorised noise and particulars of its training data, so it scores well there but generalises poorly to fresh customer data. Underfitting would instead show poor results even on the training set, which is not the case described.

  1. AUnderfitting
  2. BOverfittingCorrect
  3. CData masking
  4. DModel drift caused by regulation

Explanation

Overfitting occurs when a model captures noise and specifics of the training data and so fails to generalise to new data. Underfitting is the opposite: the model is too simple and performs poorly even on training data. Since training performance is strong here, underfitting is wrong.

Did you get it right without looking?

One question tells you little. A timed set on Artificial Intelligence - Introduction and Basics shows your real accuracy, how long you take and where you lose marks.

Practise Artificial Intelligence - Introduction and BasicsFree diagnostic mock

More Artificial Intelligence - Introduction and Basics questions