Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

WISE: Unraveling Business Process Metrics with Domain Knowledge

Urszula Jessen, Dirk Fahland

TL;DR

Evaluation using the BPIC 2019 dataset and real industrial contexts demonstrates that WISE enhances automation in business process analysis and effectively detects deviations from desired process flows.

Abstract

Anomalies in complex industrial processes are often obscured by high variability and complexity of event data, which hinders their identification and interpretation using process mining. To address this problem, we introduce WISE (Weighted Insights for Evaluating Efficiency), a novel method for analyzing business process metrics through the integration of domain knowledge, process mining, and machine learning. The methodology involves defining business goals and establishing Process Norms with weighted constraints at the activity level, incorporating input from domain experts and process analysts. Individual process instances are scored based on these constraints, and the scores are normalized to identify features impacting process goals. Evaluation using the BPIC 2019 dataset and real industrial contexts demonstrates that WISE enhances automation in business process analysis and effectively detects deviations from desired process flows. While LLMs support the analysis, the inclusion of domain experts ensures the accuracy and relevance of the findings.

WISE: Unraveling Business Process Metrics with Domain Knowledge

TL;DR

Evaluation using the BPIC 2019 dataset and real industrial contexts demonstrates that WISE enhances automation in business process analysis and effectively detects deviations from desired process flows.

Abstract

Anomalies in complex industrial processes are often obscured by high variability and complexity of event data, which hinders their identification and interpretation using process mining. To address this problem, we introduce WISE (Weighted Insights for Evaluating Efficiency), a novel method for analyzing business process metrics through the integration of domain knowledge, process mining, and machine learning. The methodology involves defining business goals and establishing Process Norms with weighted constraints at the activity level, incorporating input from domain experts and process analysts. Individual process instances are scored based on these constraints, and the scores are normalized to identify features impacting process goals. Evaluation using the BPIC 2019 dataset and real industrial contexts demonstrates that WISE enhances automation in business process analysis and effectively detects deviations from desired process flows. While LLMs support the analysis, the inclusion of domain experts ensures the accuracy and relevance of the findings.
Paper Structure (12 sections, 8 equations, 9 figures, 1 table)

This paper contains 12 sections, 8 equations, 9 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work and Problem Description
  3. Proposed method: WISE
  4. Definition of Process Norm
  5. Scores Calculation
  6. Evaluation and Results
  7. Evaluation of the BPI 2019 Dataset
  8. Comparing BPIC 2019 Reports to WISE Reporting
  9. Industrial Case Evaluation
  10. Implementation of Scoring Mechanism
  11. Results of Procurement Optimization Project
  12. Conclusion

Figures (9)

  • Figure 1: General WISE methodology and its main steps.
  • Figure 2: Structural and contextual outliers. Based on liu2022benchmarking, modified.
  • Figure 3: Scores distribution in BPIC 2019 Dataset based on the defined Process Norm.
  • Figure 4: Scores Distribution for Data from previous dataset with filter only on those with low performing scores.
  • Figure 5: Part of LLM ChatGPT4 analysis suggesting additional areas of interest and further steps.
  • ...and 4 more figures