Is there a certain threshold over which to accept or reject predictors based on correlation values with the target variable?


I have been working on the Titanic dataset. After some feature manipulation, I printed out the correlation values between my target variable Survived and all the other predictors. Based on these values, I would like to decide if any variables can be removed from the training set.

Survived  :  1.000000,
Pclass    : -0.338481,
Sex       : -0.543351,
Age       : -0.037059,
Fare      :  0.302002,
Embarked  : -0.167675,
Title     :  0.407753,
IsAlone   :  0.163157

Correlation values of Survived with other predictors.

I am not quite sure of what to do with the Age feature. Maybe try a different kind of feature manipulation on it?


Posted 2020-08-12T04:46:26.247

Reputation: 1

What does the Title column signify? is it supposed to be Ticket as per dataset. – prashant0598 – 2020-08-13T08:38:51.417

the title is basically grouping of the passengers on the categories of Mr. , Mrs. , Master and Miss – Zlatan09 – 2020-08-14T05:39:38.520

No answers