Normally,it is essential for the bins besides missing to be monotonically increasing or decreasing on the badrate for better explainability. For exmple, the bigger a certain feature X1,the better chance it might be bad sample from experience of analyst, but the training data(too small or bad distribution) cannot show this priori experience.
Wondering if the binning function could automatic handle this, make the bin of a certain select X monotonous.
Normally,it is essential for the bins besides missing to be monotonically increasing or decreasing on the badrate for better explainability. For exmple, the bigger a certain feature X1,the better chance it might be bad sample from experience of analyst, but the training data(too small or bad distribution) cannot show this priori experience. Wondering if the binning function could automatic handle this, make the bin of a certain select X monotonous.