Claudia Fracca

Ritratto Claudia Fracca

Computer Science and Innovation for Societal Challenges, XXXVI series
Grant sponsor

Massimiliano De Leoni

Project description
Business process simulation refers to techniques for the simulation of business process behavior on the basis of a business process model extended with additional information for a probabilistic characterization of the different run-time aspects (case arrival rate, task durations, routing probabilities, resource utilization, etc.). Simulation provides a flexible approach to analyse and improve business processes. Through simulation experiments, various 'what if ' questions can be answered, and redesigning alternatives can be compared with respect to some key performance indicators. The main idea of business process simulation is to generate a set of possible execution traces of a process, leveraging on the information a simulation model. The resulting execution traces allow companies to monitor the efficiency of their internal processes and to determine the critical aspects like bottlenecks, wastes, and over-and under-utilization of resources, and to verify the consequences of proposed process modifications before putting them in production. These models are typically based on insights from process documentation, expert interviews, and observations, which can provide an inaccurate process view. The literature reports on several case studies in which the perception significantly drifts apart from reality. This ultimately means that the model and the results of the simulations are not accurate. The quality of the results of process simulation is directly dependent on the quality of the simulation model. Therefore, efforts to improve simulation model realism are valuable. This project aims to build simulation models that accurately reflect the domain's reality using data kept by information systems about the daily process execution using Process Mining techniques. The key idea is that a business process simulation model can be obtained by first extracting a process model from an event log using an automated process discovery technique and then enhancing this model with simulation parameters derived from the event log, e.g., arrival rate, processing times, etc. The goal is to replace the subject perceptions with objective data. To this aim, the project will leverage Process-Mining techniques combined with Machine Learning, Artificial Intelligence, Statistical, Data Mining, and Queue Mining techniques.