journal.pone.0207806.pdf (7.31 MB)
Download file

Process mining with real world financial loan applications: Improving inference on incomplete event logs.

Download (7.31 MB)
journal contribution
posted on 10.09.2019, 13:07 by Catarina Moreira, Emmanuel Haven, Sandro Sozzo, Andreas Wichert
In this work, we analyse and model a real life financial loan application belonging to a sample bank in the Netherlands. The event log is robust in terms of data, containing a total of 262 200 event logs, belonging to 13 087 different credit applications. The goal is to work out a decision model, which represents the underlying tasks that make up the loan application service. To this end we study the impact of incomplete event logs (for instance workers forget to register their tasks). The absence of data is translated into a drastic decrease of precision and compromises the decision models, leading to biased and unrepresentative results. We use non-classical probability to show we can better reduce the error percentage of inferences as opposed to classical probability.

Funding

This work was supported by national funds through Fundação para a Ciência e a Tecnologia (FCT) with reference UID/CEC/50021/2013 (https://www.fct.pt/apoios/projectos/consulta/vglobal_projecto.phtml.en?idProjecto=147282&idElemConcurso=8957).

History

Citation

PLoS ONE, 2018, 13(12): e0207806

Author affiliation

/Organisation/COLLEGE OF SOCIAL SCIENCES, ARTS AND HUMANITIES/School of Business

Version

VoR (Version of Record)

Published in

PLoS ONE

Publisher

Public Library of Science

eissn

1932-6203

Acceptance date

06/10/2018

Copyright date

2018

Available date

10/09/2019

Publisher version

https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0207806

Notes

All relevant data will be available in the public repository: https://github.com/catarina-moreira/bpmn.

Language

en

Usage metrics

Categories

Keywords

Licence

Exports