JP Morgan Interview Questions | Dimension Reduction
Question
Why is dimension reduction important?
in progress
0
Machine Learning
55 years
4 Answers
885 views
Great Grand Master 0
Answers ( 4 )
Dimension reduction comes under feature engineering
It is the process of reducing the dimensionality of the feature space with consideration by obtaining a set of principal features.
In this way, we could remove redundant and irrelevant features without incurring much loss of information.
1) Too many features make visualizing the training set very cumbersome.
2) When no of features are large, most of them are correlated and provide redundant information.
3) Generally, we need 10 rows of data behind every feature for a ML algorithm to perform well. So,
if the no of features is very large, we might end up with insufficient amount of data to train a ML model.
4) Large no of features will take more time to train a ML model.
To avoid all the above mentioned problems, it is necessary to perform dimensionality reduction.
1. It reduce the time and storage space required.
2. Removal of multicollnearity.
3. Avoid curse of dimensionality.
4. It becomes easier to visualize
Nice and crisp !!
To the point answer