Say that I have the following set of variables:
The values represent a list of variables from a dataset. Each variable has a certain level of correlation with the target variable
$. The correlation increases or decreases depending on the sort of combination you use against your target
$. For example,
BCJX might have a higher correlation with
OQTVW. I'm going to test each possible combination against the training algorithm and output it all, with their accuracy score, in a concise CSV file. But I don't know the name of the algorithm that might combine these variables in every possible way.
In other words, I want to find the combination with the highest correlation value and the smallest dimension.