Process Mining Based Influence Analysis for Analyzing and Improving Business Processes

Teemu Lehto

Research output: ThesisDoctoral ThesisCollection of Articles

Abstract

The ability to improve processes is essential for every organization. Process mining provides a fact-based understanding of actual processes in the form of discovered process diagrams, bottlenecks, compliance issues, and other operational problems. Organizations need to carry out accurate root cause analysis and efficient resource allocation to improve the process and reduce problems. This work presents a novel influence analysis method to improve the allocation of development resources, detect process changes, and discover business areas that significantly affect process flow. The method combines the usage of process mining analysis with probability-based objective measures and analysis of deviations. The method is specially designed for business analysts, process owners, line managers, and auditors in large organizations, to be used as a set of interactive root cause analyses and benchmark reports. Methods and algorithms are presented for analyzing both binary problems where each case is either successful or non-successful, and continuous variables, including process lead times and costs. A method for using case-specific weights to consider the relative business importance of each case is also presented. This work also includes data preparation methods and best practices for acquiring relevant business operations data in the event log format. Concept drift in process mining is a research area that studies business process changes over time. This dissertation shows how process mining can be used to identify changes in business operations by using the influence analysis method to identify business process changes in the business review context. Typical business reviews consist of monitoring key performance indicator (KPI) measures against targets, while the detection of activity level process changes is often based on subjective manual observations alone. Many relevant changes are not detected promptly, making organizations slow to adapt to changes. Machine learning techniques such as clustering extend the coverage of process mining analyses. A method for clustering cases based on process flow characteristics and using influence analysis to explain the results with business attributes is presented. The method identifies business areas where the process execution differs significantly from the rest of the organization. Finally, the results of using our methods with publicly available industrial datasets, including service desk data from Rabobank, loan applications process data from a Dutch Financial Institute, and publicly available purchase to pay process data are presented.
Translated title of the contributionProsessilouhintaan perustuva vaikutusanalyysi liiketoimintaprosessien kehittämiseen.
Original languageEnglish
QualificationDoctor's degree
Awarding Institution
  • Aalto University
Supervisors/Advisors
  • Jung, Alex, Supervising Professor
  • Hollmen, Jaakko, Thesis Advisor
Publisher
Print ISBNs978-952-64-0137-9
Electronic ISBNs978-952-64-0138-6
Publication statusPublished - 2020
MoE publication typeG5 Doctoral dissertation (article)

Keywords

  • process mining
  • root cause analysis
  • process improvement
  • process analysis
  • data mining
  • influence analysis
  • machine learning
  • clustering
  • lead times

Fingerprint

Dive into the research topics of 'Process Mining Based Influence Analysis for Analyzing and Improving Business Processes'. Together they form a unique fingerprint.

Cite this