How is the data divided into splits in decision tree algorithm?

r
decision_trees

#1

cp decides the number of splits in the tree, but what exactly should be the split is decided by which factor or algorithm?


#2

@Siddhant - cp is the parameter which helps in tunning our model by which we can improve the performance of our model.

Entropy is the factor which decides the splitting of the decision tree.

For further information, you can see this post
http://discuss.analyticsvidhya.com/t/how-to-calculate-the-entropy-of-distribution-with-or-without-a-given-plot/6250

Hope this helps!

Regards,
Hinduja