A New Process Mining Approach Based on the Markov Transition Matrix

Author

Hong Li ; Kunman Li

Author_Institution

Sch. of Inf. Sci. & Eng., Yunnan Univ., Kunming, China

Volume

2

fYear

2014

fDate

10-13 March 2014

Firstpage

81

Lastpage

85

Abstract

According to the situation that many workflow instances may deviate from the predefined model, this paper proposed a new process mining approach based on analyzing the workflow log to realize the workflow process reconstruction. First, build the Markov transition matrix based on the workflow log, then design a multi-step process mining algorithm to mine the structural relationships between the activities, finally, this paper verifies the feasibility and applicability of the approach through a simulation example.

Keywords

Markov processes; business data processing; data mining; matrix algebra; workflow management software; Markov transition matrix; business process automated execution; information technology; multistep process mining algorithm; new process mining approach; workflow management systems; workflow process reconstruction; Algorithm design and analysis; Computational modeling; Contracts; Data mining; Markov processes; Noise; markov transition matrix; process mining; process reconstruction;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Science and Computational Intelligence (CSCI), 2014 International Conference on

Conference_Location

Las Vegas, NV

Type

conf

DOI

10.1109/CSCI.2014.99

Filename

6822308