Skip to content

FRM Part II · FRM Exam Part II · Advances in Artificial Intelligence: Implications for Capital Markets Activities

An AI model used for anti-money-laundering screening was trained on historical alerts that analysts had closed. Over time, its alert rate on a particular customer segment falls sharply, though no change in the segment's behaviour is evident. Which is the most likely risk and best first action?

The likely cause is bias or a feedback loop from training on past analyst closures, which teaches the model to under-flag the segment. The best first step is validation and outcome testing on that segment, not ignoring the drop or making the model more complex.

  1. AData drift only; ignore it as the model is self-correcting
  2. BBias or feedback-loop effects from training on past analyst decisions; investigate through validation and outcome testing on the segmentCorrect
  3. COverfitting to future data; increase the model's complexity
  4. DHardware failure; restart the system

Explanation

Training on historical analyst closures can embed past judgements and create feedback loops that under-flag segments. The right response is targeted validation and outcome testing, not ignoring it or adding complexity.

Did you get it right without looking?

One question tells you little. A timed set on Advances in Artificial Intelligence: Implications for Capital Markets Activities shows your real accuracy, how long you take and where you lose marks.

Practise Advances in Artificial Intelligence: Implications for Capital Markets ActivitiesFree diagnostic mock

More Advances in Artificial Intelligence: Implications for Capital Markets Activities questions