A Data Driven Agent Elicitation Pipeline for Prediction Models

John Bruntse Larsen, Andrea Burattin, Christopher John Davis, Rasmus Hjardem-Hansen, Jørgen Villadsen

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

Agent-based simulation is a method for simulating complex systems by breaking them down into autonomous interacting agents. However, to create an agent-based simulation for a real-world environment it is necessary to carefully design the agents. In this paper we demonstrate the elicitation of simulation agents from real-world event logs using process mining methods. Collection and processing of event data from a hospital emergency room setting enabled real-world event logs to be synthesized from observational and digital data and used to identify and delineate simulation agents.
Original languageEnglish
Title of host publicationBusiness Process Management Workshops
EditorsC. Di Francescomarino , R. Dijkman , U. Zdun
PublisherSpringer
Publication date2020
Pages570-582
ISBN (Print)978-3-030-37452-5
DOIs
Publication statusPublished - 2020
Event17th Int. Conference on Business Process Management
- Vienna University of Economics and Business, Vienna, Austria
Duration: 1 Sep 20196 Sep 2019
Conference number: 17

Conference

Conference17th Int. Conference on Business Process Management
Number17
LocationVienna University of Economics and Business
CountryAustria
CityVienna
Period01/09/201906/09/2019
SeriesLecture Notes in Business Information Processing
Volume362
ISSN1865-1348

Keywords

  • Agent-based simulation
  • Process mining
  • Emergency Rooms

Fingerprint Dive into the research topics of 'A Data Driven Agent Elicitation Pipeline for Prediction Models'. Together they form a unique fingerprint.

Cite this