hard · FRM Part 1
An analyst is using a k-nearest neighbors (kNN) algorithm to classify credit defaults.
If k is set to a very low value (e.g., k=1), what is the likely impact on the model's performance?
- Increased computational efficiency during the training phase.
- The model becomes equivalent to a linear regression.
- Low bias and high variance (overfitting).
- High bias and low variance.
Sign up free to see the explanation and track your rank →
More FRM Part 1 practice
- According to the CAPM, which type of risk are investors compensated for bearing?
- What specific variety of liquidity risk is being described?
- How is 'Risk Capacity' distinguished from 'Risk Appetite' in a standard risk governance fr
- If a loan has a Probability of Default (PD) of 2.0%, an Exposure at Default (EAD) of $1,00
- If two portfolios have the same Sharpe ratio but one has positive skewness and the other h
- In a 'Liquidity Spiral', what is the primary channel by which market liquidity risk and fu
- In the context of the CAPM, what is the definition of 'Alpha' (α)?
- In the risk decomposition formula σ^2_i = β^2_i σ^2_M + σ^2_ε, what does σ^2_ε represent?