I am just learning about machine learning (no pun intended). I have used xgboost's objective function binary:logistic to find probabilities from labels of 0s and 1s. Is there some way to guide the objective function to maximize a sum instead of decreasing error based upon the label? If each label has a corresponding value I'd like this number to be as high as possible. Error be damned. I still want to know the probability from binary:logistic, I just want it to give me the probability associated with the highest sum.
Any guidance is much appreciated.