PLoS ONE (Jan 2018)

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

  • Catarina Moreira,
  • Emmanuel Haven,
  • Sandro Sozzo,
  • Andreas Wichert

DOI
https://doi.org/10.1371/journal.pone.0207806
Journal volume & issue
Vol. 13, no. 12
p. e0207806

Abstract

Read online

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.