Quantcast
Channel: Data Science, Analytics and Big Data discussions - Latest topics
Viewing all articles
Browse latest Browse all 4448

Why are numerical fields dropped and just a "present or not" indicator flag used in their place?

$
0
0

@javadba wrote:

I was looking at an older post on GBM parameter tuning techniques on Housing dataset: https://www.analyticsvidhya.com/blog/2016/02/complete-guide-parameter-tuning-gradient-boosting-gbm-python/

What I noticed is that a number of numerical fields that would seem useful for prediction purposes were scrapped in favor of flags indicating they were present or not. Here is one of them:

  1. Loan_Amount_Submitted_Missing created which is 1 if Loan_Amount_Submitted was missing else 0 | Original variable Loan_Amount_Submitted dropped

I would think the Loan amount would be huge for predicting loan conversion rate. So why was that field dropped?

Posts: 1

Participants: 1

Read full topic


Viewing all articles
Browse latest Browse all 4448

Trending Articles