CoSMo: a Framework to Instantiate Conditioned Process Simulation Models

TL;DR

CoSMo introduces a novel neural architecture that enables the simulation of process models conditioned on user-defined constraints, enhancing the ability to perform targeted what-if analyses in business process simulation.

Contribution

The paper presents a new recurrent neural network framework that integrates declarative rules into process simulation, addressing limitations of existing data-driven and deep learning approaches.

Findings

CoSMo effectively simulates event logs under specific constraints.

The architecture successfully incorporates declarative rules into deep learning models.

Experimental results demonstrate improved control over simulation outputs.

Abstract

Process simulation is gaining attention for its ability to assess potential performance improvements and risks associated with business process changes. The existing literature presents various techniques, generally grounded in process models discovered from event log data or built upon deep learning algorithms. These techniques have specific strengths and limitations. Traditional data-driven approaches offer increased interpretability, while deep learning-based excel at generalizing changes across large event logs. However, the practical application of deep learning faces challenges related to managing stochasticity and integrating information for what-if analysis. This paper introduces a novel recurrent neural architecture tailored to discover COnditioned process Simulation MOdels (CoSMo) based on user-based constraints or any other nature of a-priori knowledge. This architecture facilitates the simulation of event logs that adhere to specific constraints by incorporating declarative-based rules into the learning phase as an attempt to fill the gap of incorporating information into deep learning models to perform what-if analysis. Experimental validation illustrates CoSMo's efficacy in simulating event logs while adhering to predefined declarative conditions, emphasizing both control-flow and data-flow perspectives.