For the k-NN algorithm, what could be a potential drawback of using a very large value of k?

  • Decreased Model Sensitivity
  • Improved Generalization
  • Increased Computational Cost
  • Reduced Memory Usage
A large value of k in k-NN can make the model less sensitive to local patterns, leading to a loss in predictive accuracy due to averaging over more neighbors.
Add your answer
Loading...

Leave a comment

Your email address will not be published. Required fields are marked *