Monotone Functions and Expert Models for Explanation of Machine Learning Models

There are significant difficulties for the acceptance of black-box Machine Learning (ML) models by subject matter experts (SMEs) despite significant achievements of many black-box models. A promising way to address this problem is by building a trustable, qualitative, interpretable models for the task based on SME knowledge. Such qualitative models can work as qualitative explainers of black-box models or as sanity checks for them. In this paper, qualitative models operate with ordinal attributes, which can be Boolean or k-valued attributes with a small $k$. Humans easier understand and reason with such attributes that with continuous numeric attributes with many more values. Some ML tasks do not have sufficient training data. Building qualitative models with a SME (“expert models”) is a way to solve these tasks solely with a SME's knowledge. The proposed Monotone Ordinal Expert Knowledge Acquisition (MOEKA) system allows building “expert models” through interview phases with the SME. Monotonicity is a key property of the system that is tested and used to shorten the interview process with a SME along with new methods for selecting the order of questions. MOEKA rather directly approximates domain knowledge in contrast with other ML explainers, which approximate black-box ML models. MOEKA can be also used as a method of database searching. Several case studies on gout, diabetes, and housing demonstrate efficiency of MOEKA.