Skip to content

ACCA Strategic Professional · Strategic Business Leader · Big data and data analytics

Orchard Health Insurer's fraud team reviews claims manually. It wants to analyse the whole text of millions of claim notes and call transcripts to spot unusual wording linked to previously confirmed fraud cases. Which approach best fits this need?

Text analytics using natural language processing, trained on labelled past fraud cases, fits best. The data is unstructured text, which structured summaries such as OLAP cubes cannot analyse. Confirmed fraud cases give labels for a model to learn suspicious wording; scorecards and budget sensitivity do not analyse text.

  1. AText analytics using natural language processing, trained on labelled past fraud casesCorrect
  2. BOnline analytical processing cubes summarising claim values by region
  3. CA balanced scorecard of claim-handling performance
  4. DSensitivity analysis of the insurer's annual budget

Explanation

Claim notes and transcripts are unstructured text, so text analytics with natural language processing is needed; labelled past fraud cases allow a supervised model. OLAP cubes summarise structured numeric data. A scorecard and budget sensitivity are not data mining techniques for text.

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.

Practise Big data and data analyticsFree diagnostic mock

More Big data and data analytics questions