Skip to content

IAI Actuarial Core Principles · Risk Modelling and Survival Analysis · Elementary principles of machine learning

A model predicting whether a policy lapses is tested on 1,000 policies, of which 100 actually lapse. The model predicts lapse for 80 policies, 60 of which really lapse. Which row gives the correct precision and recall for the lapse class?

Precision is 0.75 and recall is 0.60. Precision divides the 60 correct lapse predictions by the 80 predicted lapses, while recall divides the same 60 by the 100 policies that actually lapsed. Swapping the denominators gives the wrong pairing.

  1. APrecision 0.60, recall 0.75
  2. BPrecision 0.75, recall 0.60Correct
  3. CPrecision 0.75, recall 0.80
  4. DPrecision 0.60, recall 0.60
  5. Precision 0.94, recall 0.75

Explanation

True positives = 60. Precision = TP / predicted positives = 60/80 = 0.75. Recall = TP / actual positives = 60/100 = 0.60. The option with 0.60 and 0.75 swaps the two measures, and 0.94 is overall accuracy-type reasoning: (60+880)/1000 = 0.94, not precision.

Did you get it right without looking?

One question tells you little. A timed set on Elementary principles of machine learning shows your real accuracy, how long you take and where you lose marks.

Practise Elementary principles of machine learningFree diagnostic mock

More Elementary principles of machine learning questions