Title: Heuristic rule-based process discovery approach from events data

Authors: Hind R'bigui; Chiwoon Cho

Addresses: School of Industrial Engineering, University of Ulsan, Ulsan 680-749, South Korea ' School of Industrial Engineering, University of Ulsan, Ulsan 680-749, South Korea

Abstract: Knowledge management consists of transforming data into beneficial knowledge in a business environment. Today, large amounts of data related to the execution of business processes called event logs are stored in the information systems. Process mining enables knowledge management by extracting knowledge from these historical event logs. Most organisations seek to understand how their business processes are executed to improve them. Therefore, several process discovery techniques have been developed in the field of process mining. However, none of the existing algorithms can discover all types of process constructs that can exist in an event log in a restricted time. This paper proposes a new heuristic rule-based technique that is capable of constructing process models with standard constructs, short loops, invisible tasks, duplicate tasks, and non-free choice constructs. Artificial and real-life data have been used to evaluate the algorithm. The results demonstrate that the aforementioned characteristics can be discovered correctly.

Keywords: process mining; knowledge discovery; process modelling; invisible tasks; duplicate tasks; short loops; non-free choice; process discovery; event logs; heuristic rules.

DOI: 10.1504/IJTPM.2019.104060

International Journal of Technology, Policy and Management, 2019 Vol.19 No.4, pp.352 - 391

Received: 16 Dec 2017
Accepted: 22 Apr 2018

Published online: 07 Dec 2019 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article