Snapdeal Interview Question | Feature Selection
Question
Prior to building any kind of model, why do we need to complete the feature selection step? What will happen if we skip it?
in progress
0
Machine Learning
55 years
1 Answer
902 views
Great Grand Master 0
Answer ( 1 )
Feature Selection is the most important part of modelling in Machine Learning, if we skip it then there might be chances of the following:
1. There are some columns in the data that are irrelevant and if we keep them in our dataset they might act as a noise to the data.
2. If we do not do feature selection then the data might have multicollinearity which will effect the modelling score afterwads.
3. If we select the most relevant features then our model will learn more efficiently.