Quantifying and Explaining Machine Learning Uncertainty in Predictive Process Monitoring: An Operations Research Perspective

TL;DR

This paper presents a comprehensive machine learning framework that quantifies and explains uncertainty in predictive process monitoring, integrating interval predictions and explainability techniques to improve decision-making in operations research.

Contribution

It introduces a novel multi-stage methodology combining Quantile Regression Forests and SHAP explanations to address limitations of existing models in uncertainty estimation and interpretability.

Findings

Effective interval predictions for process monitoring

Enhanced explainability of model uncertainty sources

Improved decision-making in a real-world case study

Abstract

This paper introduces a comprehensive, multi-stage machine learning methodology that effectively integrates information systems and artificial intelligence to enhance decision-making processes within the domain of operations research. The proposed framework adeptly addresses common limitations of existing solutions, such as the neglect of data-driven estimation for vital production parameters, exclusive generation of point forecasts without considering model uncertainty, and lacking explanations regarding the sources of such uncertainty. Our approach employs Quantile Regression Forests for generating interval predictions, alongside both local and global variants of SHapley Additive Explanations for the examined predictive process monitoring problem. The practical applicability of the proposed methodology is substantiated through a real-world production planning case study, emphasizing the potential of prescriptive analytics in refining decision-making procedures. This paper accentuates the imperative of addressing these challenges to fully harness the extensive and rich data resources accessible for well-informed decision-making.