Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Identifying Process Improvement Opportunities through Process Execution Benchmarking

Luka Abb, Majid Rafiei, Timotheus Kampik, Jana-Rebecca Rehse

TL;DR

The paper tackles the gap in traditional process benchmarking that reports indicators but not concrete improvement actions. It introduces a prescriptive technique, process execution benchmarking, that compares an own event log with a benchmark log to identify behaviorally plausible activity replacements and assesses their feasibility and performance impact via trace alignments and behavioral footprints. The contributions include a five-step method to derive compatible sets of replacements, along with feasibility and impact measures, demonstrated on synthetic data with high precision and in a SAP Signavio case study showing actionable results. This approach provides evidence-based, actionable guidance for process managers to implement targeted improvements and close performance gaps in real-world settings.

Abstract

Benchmarking functionalities in current commercial process mining tools allow organizations to contextualize their process performance through high-level performance indicators, such as completion rate or throughput time. However, they do not suggest any measures to close potential performance gaps. To address this limitation, we propose a prescriptive technique for process execution benchmarking that recommends targeted process changes to improve process performance. The technique compares an event log from an ``own'' process to one from a selected benchmark process to identify potential activity replacements, based on behavioral similarity. It then evaluates each proposed change in terms of its feasibility and its estimated performance impact. The result is a list of potential process modifications that can serve as evidence-based decision support for process improvement initiatives.

Identifying Process Improvement Opportunities through Process Execution Benchmarking

TL;DR

The paper tackles the gap in traditional process benchmarking that reports indicators but not concrete improvement actions. It introduces a prescriptive technique, process execution benchmarking, that compares an own event log with a benchmark log to identify behaviorally plausible activity replacements and assesses their feasibility and performance impact via trace alignments and behavioral footprints. The contributions include a five-step method to derive compatible sets of replacements, along with feasibility and impact measures, demonstrated on synthetic data with high precision and in a SAP Signavio case study showing actionable results. This approach provides evidence-based, actionable guidance for process managers to implement targeted improvements and close performance gaps in real-world settings.

Abstract

Benchmarking functionalities in current commercial process mining tools allow organizations to contextualize their process performance through high-level performance indicators, such as completion rate or throughput time. However, they do not suggest any measures to close potential performance gaps. To address this limitation, we propose a prescriptive technique for process execution benchmarking that recommends targeted process changes to improve process performance. The technique compares an event log from an ``own'' process to one from a selected benchmark process to identify potential activity replacements, based on behavioral similarity. It then evaluates each proposed change in terms of its feasibility and its estimated performance impact. The result is a list of potential process modifications that can serve as evidence-based decision support for process improvement initiatives.

Paper Structure

This paper contains 16 sections, 8 equations, 4 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Problem Illustration
  3. Foundations
  4. Technique
  5. Computing Behavioral Footprints
  6. Matching Activities between Logs
  7. Combining Compatible Matches
  8. Assessing the Feasibility of Process Changes
  9. Assessing the Performance Impact of Process Changes
  10. End Result
  11. Discussion
  12. Evaluation
  13. Experiment
  14. Case study
  15. Related Work
  16. ...and 1 more sections

Figures (4)

  • Figure 1: Running example own and benchmark versions of a (simplified) purchasing process in an SAP ERP system. Disparities are highlighted in blue.
  • Figure 2: High-level overview of the proposed technique and intermediary results
  • Figure 3: Matching activities between footprint matrices to find behaviorally plausible replacements in the running example.
  • Figure 4: Matches, compatibility graph, and maximal compatible replacements from the running example. Fully connected subgraphs are also considered changes.