You notice that your KNN model is highly sensitive to outliers. What might be causing this, and how could the choice of K and distance metric help in alleviating this issue?
- Choose a larger K and an appropriate distance metric to mitigate sensitivity
- Choose a small K and ignore outliers
- Focus only on the majority class
- Outliers have no effect
Choosing a larger K and an appropriate distance metric can help mitigate the sensitivity to outliers, as it would reduce the influence of individual data points.
Loading...
Related Quiz
- You are asked to apply Hierarchical Clustering to a dataset with mixed types of data (categorical and numerical). What challenges could arise and how would you tackle them?
- What is the principle behind the Random Forest algorithm?
- Cross-Validation divides the dataset into "k" subsets, or _______, where one subset is used as the validation set, and the rest are used for training.
- You are implementing LDA, but the assumptions regarding normality and equal covariance matrices are not met. How will this affect the results, and what can be done?
- A financial institution wants to reduce the false positives in its existing fraud detection system. How would Machine Learning help in this scenario?