Integration of System Dynamics and Process Mining Approaches for Uncertainty Management

Abstract

Complex systems generally contain uncertainty, which stems from incomplete information, variability, and randomness. Process mining addresses uncertainty in business process management, particularly in identifying process models, while system dynamics provides a framework for modeling and simulating complex systems to predict future outcomes. This paper examines the merging of system dynamics and process mining in managing uncertainty, highlighting key trends: extended decision support systems, probabilistic modeling and simulation, and predictive analytics. It also discusses challenges associated with these trends and identifies future research directions. The paper emphasizes the need for refining techniques, algorithms, and frameworks for integrating system dynamics models with process mining insights for uncertainty management in complex systems. Suggested improvements include validation techniques for uncertainty, synchronization of data events with simulation time frames, management of time delays, and capturing temporal patterns. Additionally, the paper calls for methods to quantify uncertainty, perform sensitivity analysis, and assess the impact of uncertainty on model predictions and decision-making. These advancements could significantly enhance the integration of system dynamics and process mining in uncertain environments.