Skip to content

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

A firm trains a return-forecasting model using data on firms that are still listed today, excluding companies that were delisted or went bankrupt during the sample. Which bias does this introduce, and what is its likely effect?

This is survivorship bias, which tends to overstate model performance. By excluding delisted or bankrupt firms, the training data contains only winners that survived, so historical outcomes look better than a real-time investor would have experienced and the model's apparent skill is inflated.

  1. ASurvivorship bias, which tends to overstate model performanceCorrect
  2. BLook-ahead bias, which tends to understate model performance
  3. CSelection of too many features, which causes underfitting
  4. DLabel imbalance, which always lowers recall to zero

Explanation

Excluding failed firms leaves only survivors, making historical returns and the model's apparent skill look better than they would have been in real time. Look-ahead bias concerns using information not available at the time, which is a different problem.

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