why is it difficult for the algorithm to work on unnormalized data? what is the core reason behind scaling your data?
Why do we do normailization or standardization?
It is not true that all algorithms didn’t work on unnormalized data, decision trees is one of the algorithm that can work on unnormalized data. While others like KNN, Linear Regression etc are unable to do.
For Eg: lets perform a basic knn algorithms on a dataset comprising of child age in yrs, and child height in cm. Now if you would perform knn without normalizing the data, now suppose you calculate normal euclidean distance. It is quite obvious that while calculating distance, difference in heights would share a major part of distance and hence even if change age difference by slight value, net euclidean distance would hardly have any effect.
So to scale each and every feature on a similar scale with use normalization and standardization
1 Like
I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.
On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.