1
$\begingroup$

I've heard from multiple sources that it depends on whether I should standardize or not. Most of the time, people would say it doesn't make sense to do so, some would say it's better if I standardize it because it makes doing gradient descent better, etc.

However, I was messing around with it with my data set, and I learned that if I standardize my target, find the RMSE, and then un-standardize my RMSE (I multiply it with the standard deviation), it's the same as the RMSE of an un-standardized target. I mean it would make sense that it's the same because mathematically it's kinda like un-z-scoring a z score to get the raw data. But, I'm not sure.

So, is standardizing the target completely useless? Or is standardizing the target help make the model better in the sense that it's faster? Or am I doing something wrong?

$\endgroup$
3
  • $\begingroup$ good question - Z score interpretation $\endgroup$ Jan 4 at 10:18
  • $\begingroup$ and then un-standardize my RMSE (I multiply it with the standard deviation), it's the same as the RMSE of an un-standardized target. I am not sure, it produces the un-standardized RMSE. $\endgroup$ Jan 4 at 10:22
  • $\begingroup$ "standardizing the target is completely useless". Can not say what do you want to propagate? $\endgroup$ Jan 4 at 10:28

0

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.