Measuring Classification Decision Certainty and Doubt
Alexander Berenbeim, Iain J. Cruickshank, Susmit Jha, Robert Thomson, Nathaniel D. Bastian · arXiv (Cornell University) · 2023
Quantitative characterizations and estimations of uncertainty are of fundamental importance in optimization and decision-making processes. Herein, we propose intuitive scores, which we call certainty and doubt, that can be used in both a Bayesian and frequentist framework to assess and compare the quality and uncertainty of predictions in (multi-)classification decision machine learning problems.