Skip to content

ACCA Applied Skills · Performance Management · Big data and data analytics

A manufacturer's analysts build a predictive model using five years of sales data from a period in which one competitor dominated the market. The competitor has now exited and three new rivals have entered. Which limitation of big data analysis is MOST relevant to the reliability of the model's forecasts?

The key limitation is that historical data may not reflect future conditions. The model learned patterns from a market with one dominant competitor, and with that competitor gone and new rivals present, those relationships may no longer hold, making forecasts unreliable.

  1. AHistorical data may not represent future conditions, so the model's patterns may no longer holdCorrect
  2. BThe model cannot use data older than one year
  3. CPredictive models can only be run on unstructured data
  4. DBig data always understates the volume of sales

Explanation

Predictive models extrapolate patterns from past data. A structural change in the market means relationships in the historic data may no longer apply, so forecasts could be misleading. The other options are false statements about analytics.

Did you get it right without looking?

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

More Big data and data analytics questions