D Cube Analytics Interview Question | Mean Square Error

Question

Why is mean square error a bad measure of model performance? What would you suggest instead?

in progress 0
Dhruv2301 4 years 1 Answer 689 views Great Grand Master 0

Answer ( 1 )

  1. There is no correct value for MSE. Simply put, the lower the value the better, and 0 means the model is perfect. Since there is no correct answer, the MSE’s basic value is in selecting one prediction model over another.
    Adjusted R2 is a better option instead

  2. Mean square error very much sensitive to outlier if there are any outliers in the error MSE can’t handle those things so we prefer Median absolute deviation(MAD)

Leave an answer

Browse
Browse