# Learning Accurate Business Process Simulation Models from Event Logs via Automated Process Discovery and Deep Learning

arXiv: https://arxiv.org/abs/2103.11944 · HTML: https://mlsanity.com/paper/2103.11944/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 29 references that are in the map.
- First posted on arXiv 22 Mar 2021.

## Builds on (most cited first, 9 of 9)

- [Predictive Business Process Monitoring with LSTM Neural Networks](https://mlsanity.com/paper/1612.02130/) (2016)
- [Predicting Process Behaviour using Deep Learning](https://mlsanity.com/paper/1612.04600/) (2016)
- [Deep Learning for Predictive Business Process Monitoring: Review and Benchmark](https://mlsanity.com/paper/2009.13251/) (2020)
- [Predictive Business Process Monitoring via Generative Adversarial Nets: The Case of Next Event Prediction](https://mlsanity.com/paper/2003.11268/) (2020)
- [Automated Discovery of Business Process Simulation Models from Event Logs](https://mlsanity.com/paper/1910.05404/) (2019)
- [An Interdisciplinary Comparison of Sequence Modeling Methods for Next-Element Prediction](https://mlsanity.com/paper/1811.00062/) (2018)
- [Discovering Generative Models from Event Logs: Data-driven Simulation vs Deep Learning](https://mlsanity.com/paper/2009.03567/) (2020)
- [Scalable Alignment of Process Models and Event Logs: An Approach Based on Automata and S-Components](https://mlsanity.com/paper/1910.09767/) (2019)
- [Discovering Business Process Simulation Models in the Presence of Multitasking](https://mlsanity.com/paper/2004.09138/) (2020)

## Built on by (most cited first, 11 of 11)

- [AgentSimulator: An Agent-based Approach for Data-driven Business Process Simulation](https://mlsanity.com/paper/2408.08571/) (2024)
- [Machine learning in business process management: A systematic literature review](https://mlsanity.com/paper/2405.16396/) (2024)
- [Large Process Models: A Vision for Business Process Management in the Age of Generative AI](https://mlsanity.com/paper/2309.00900/) (2023)
- [Enhancing Business Process Simulation Models with Extraneous Activity Delays](https://mlsanity.com/paper/2206.14051/) (2022)
- [Discovery and Simulation of Data-Aware Business Processes](https://mlsanity.com/paper/2408.13666/) (2024)
- [Automated decision-making for dynamic task assignment at scale](https://mlsanity.com/paper/2504.19933/) (2025)
- [Analysis of business process automation as linear time-invariant system network](https://mlsanity.com/paper/2302.04785/) (2023)
- [CoSMo: a Framework to Instantiate Conditioned Process Simulation Models](https://mlsanity.com/paper/2303.17879/) (2023)
- [Rethinking BPS: A Utility-Based Evaluation Framework](https://mlsanity.com/paper/2505.22316/) (2025)
- [A Divide-and-Conquer Approach for Modeling Arrival Times in Business Process Simulation](https://mlsanity.com/paper/2505.22381/) (2025)
- [Relational Learning as World Modeling](https://mlsanity.com/paper/2610.16763/) (2026)

## Abstract (arXiv)

Business process simulation is a well-known approach to estimate the impact of changes to a process with respect to time and cost measures -- a practice known as what-if process analysis. The usefulness of such estimations hinges on the accuracy of the underlying simulation model. Data-Driven Simulation (DDS) methods leverage process mining techniques to learn process simulation models from event logs. Empirical studies have shown that, while DDS models adequately capture the observed sequences of activities and their frequencies, they fail to accurately capture the temporal dynamics of real-life processes. In contrast, generative Deep Learning (DL) models are better able to capture such temporal dynamics. The drawback of DL models is that users cannot alter them for what-if analysis due to their black-box nature. This paper presents a hybrid approach to learn process simulation models from event logs wherein a (stochastic) process model is extracted via DDS techniques, and then combined with a DL model to generate timestamped event sequences. An experimental evaluation shows that the resulting hybrid simulation models match the temporal accuracy of pure DL models, while partially retaining the what-if analysis capability of DDS approaches.