-1
Hey guys, I have a question for my TCC.
I have a database of customer information and loans, which indicates whether or not the customer has paid a requested loan, containing various customer information.
I must divide this database into 4, as if it represented 4 banks of different customer profiles. I will use the k-Means algorithm to make this division.
My question is: should I perform the whole procedure of data pre-processing (cleaning, filtering, normalization) or if I apply the raw dataset in the algorithm I will get a good result in my grouping?