Your KNN classifier has 50 features, but you suspect many are irrelevant and degrading performance. You need to design a feature selection strategy that works well with KNN. Which approach is most effective?

Question

Answer

Use a wrapper method: iteratively evaluate subsets of features using KNN's cross-validated accuracy as the scoring function, selecting the subset that maximises performance

Answer

Remove features one at a time based on their individual correlation with the target

Answer

Use PCA to reduce to 2 components regardless of explained variance, then run KNN

Answer

Keep all 50 features but increase K to compensate for noise

Crowdly

Your KNN classifier has 50 features, but you suspect many are irrelevant and deg...

Want instant access to all verified answers on moodle.ucu.ac.ug?