Loading...

Business Processes Deviation Analysis Using Process Mining Algorithms

Attarzadeh, Milad | 2024

0 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 57753 (01)
  4. University: Sharif University of Technology
  5. Department: Industrial Engineering
  6. Advisor(s): Akbari Jokar, Mohammad Reza; Hassannayebi, Erfan
  7. Abstract:
  8. Deviations in business processes consistently impose significant financial and temporal costs on business owners and can lead to decreased customer satisfaction with organizations. Therefore, timely identification of deviations is a crucial and significant issue for business process managers. While extensive research has been conducted on the detection of antecedent deviations, predicting deviations before they occur—which could facilitate preemptive actions to prevent these deviations—has received less attention. In this context, the aim of this study is to predict two types of process deviations—temporal deviations and Rework deviations—using machine learning and deep learning algorithms, and to compare their performance. The study employed XGBoost, RandomForest, and SVC (machine learning algorithms) as well as LSTM (a deep learning algorithm), and evaluated their performance using real data from the purchase order process, consisting of 191,139 events. The results indicate that XGBoost and LSTM demonstrated the best performance in predicting deviations in a close competition. Specifically, for predicting temporal deviations, the LSTM algorithm achieved the highest performance with a coverage metric of 0.95, an AUC of 0.80, and an F1 score of 0.80. For predicting deviations in repetitive activities, the XGBoost algorithm performed the best overall, with a coverage metric of 0.95, an AUC of 0.94, and an F1 score of 0.90
  9. Keywords:
  10. Business Process ; Business Process Management System ; Process Mining ; Predictive Process Monitoring ; Machine Learning ; Deep Learning ; Process Deviations

 Digital Object List

 Bookmark

No TOC