Quantifying and Explaining Machine Learning Uncertainty in Predictive Process Monitoring: An Operations Research Perspective
This work addresses the challenge of improving decision-making in operations research by providing uncertainty-aware predictions and explanations, though it is incremental as it builds on existing methods like Quantile Regression Forests and SHAP.
The paper tackles the problem of predictive process monitoring in operations research by addressing limitations like neglecting data-driven parameter estimation and lacking uncertainty quantification and explanations, resulting in a framework that uses Quantile Regression Forests and SHAP for interval predictions and explanations, validated in a real-world production planning case study.
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.