Most machine learning models have some ability to do this built-in, but the problem is that the confidence scores are generally "poorly calibrated" in that they do not correspond to useful estimates of probabilities.

I've always been surprised at how little interest industry seems to have in probabilistic machine learning, and how it seems to be almost absent from standard data science curricula. It can matter a lot in solving real world problems, but it can be harder to develop and validate a model that emits probabilities you can actually trust.