Skip to content

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

A trading firm uses a natural language processing model to turn news and social media into trading signals. Which control is most appropriate to address the risk that the model acts on fabricated or manipulated content?

Source verification, anomaly filtering of inputs and hard position limits with kill switches are most appropriate. They reduce the chance that fabricated or manipulated text drives trades and cap losses if the model is fooled, unlike looser limits or reliance on back-test performance.

  1. AIncrease the model's trading limits so it can exploit mispricing faster
  2. BRemove human oversight to reduce latency
  3. CApply source verification, anomaly filters on signal inputs and pre-set position and kill-switch limitsCorrect
  4. DRely solely on back-test Sharpe ratio for approval

Explanation

Text-driven signals are vulnerable to misinformation and adversarial manipulation. Input validation, source credibility checks and hard risk limits with kill switches limit the damage. Higher limits and removing oversight increase exposure, and a back-test ratio does not test manipulation.

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