Skip to content

ACCA Strategic Professional · Advanced Performance Management · Technology and information systems

Zentra Retail plc wants its finance team to forecast monthly sales for each of its 400 stores using five years of historical sales, local weather, promotions and holiday calendars. The model will be trained on past data in which the actual sales outcomes are known. Which type of machine learning is being used?

This is supervised learning. The model is trained on historical data in which the actual sales outcomes are already known, so it learns the relationship between inputs and a labelled target and then predicts future store sales. Unsupervised learning would have no known target variable.

  1. AUnsupervised learning, because the model finds its own groupings in the data
  2. BSupervised learning, because the model learns from labelled historical outcomes to predict a known targetCorrect
  3. CReinforcement learning, because the model is rewarded for each correct store forecast through trial and error
  4. DRule-based automation, because the model follows fixed instructions written by finance staff

Explanation

Training on historical data where the sales outcome (the target) is known is supervised learning. Unsupervised learning has no labelled target and looks for structure such as clusters. Reinforcement learning relies on an agent receiving rewards through interaction with an environment, which is not the case here.

Did you get it right without looking?

One question tells you little. A timed set on Technology and information systems shows your real accuracy, how long you take and where you lose marks.

Practise Technology and information systemsFree diagnostic mock

More Technology and information systems questions