# Discovering Generative Models from Event Logs: Data-driven Simulation vs Deep Learning

arXiv: https://arxiv.org/abs/2009.03567 · HTML: https://mlsanity.com/paper/2009.03567/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Sep 2020.

## Built on by (most cited first, 8 of 8)

- [Learning Accurate Business Process Simulation Models from Event Logs via Automated Process Discovery and Deep Learning](https://mlsanity.com/paper/2103.11944/) (2021)
- [Can I Trust My Simulation Model? Measuring the Quality of Business Process Simulation Models](https://mlsanity.com/paper/2303.17463/) (2023)
- [Enhancing Business Process Simulation Models with Extraneous Activity Delays](https://mlsanity.com/paper/2206.14051/) (2022)
- [Generating the Traces You Need: A Conditional Generative Model for Process Mining Data](https://mlsanity.com/paper/2411.02131/) (2024)
- [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 Unified Particle Filter LSTM for Data-Driven Process Simulation](https://mlsanity.com/paper/2609.01967/) (2026)

## Abstract (arXiv)

A generative model is a statistical model that is able to generate new data instances from previously observed ones. In the context of business processes, a generative model creates new execution traces from a set of historical traces, also known as an event log. Two families of generative process simulation models have been developed in previous work: data-driven simulation models and deep learning models. Until now, these two approaches have evolved independently and their relative performance has not been studied. This paper fills this gap by empirically comparing a data-driven simulation technique with multiple deep learning techniques, which construct models are capable of generating execution traces with timestamped events. The study sheds light into the relative strengths of both approaches and raises the prospect of developing hybrid approaches that combine these strengths.