Skip to content

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

A firm adds an L1 (lasso) penalty to a regression-based machine learning model with 200 candidate predictors. Compared with an unpenalized model, what is the primary effect of the L1 penalty?

The L1 penalty shrinks coefficients and sets some exactly to zero, effectively selecting variables and reducing overfitting. It does not equalize coefficients, does not increase variance, and does not remove the need for out-of-sample validation.

  1. AIt drives some coefficients exactly to zero, performing variable selection and reducing overfittingCorrect
  2. BIt guarantees all 200 coefficients become equal in magnitude
  3. CIt removes the need for out-of-sample testing
  4. DIt increases variance by allowing larger coefficients

Explanation

The L1 penalty adds the sum of absolute coefficients to the loss, shrinking coefficients and setting some exactly to zero. This gives a sparser model with lower variance. It does not remove the need for out-of-sample testing.

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