Do we scale the features assuming all the features have the same amount of influence on the result?

[rmwkwok]

Hello @Govarthenan_Rajadura,

@Govarthenan_Rajadura

But what if, in real life, one variable contributed more to a house’s price than the other?

We will let the the features’ associated weights to decide what contribute more. Since it is the training algorithm and the training dataset that decide the optimal weights, we are actually letting the algorithm and the data to decide what contribute more.

@Govarthenan_Rajadura

So why do we do feature scaling? Why is this an almost-standard pre-processing procedure?

Because we want to train the model more efficiently. The slide included in this post should explain that. You might read the post for more, or go back to that video for Andrew’s explanation.

In short, the focus here is about training efficiency. Your concern of what contributes more is addressed by the weights.

Cheers,
Raymond