Enabling efficient business process mining using flatten sequential structure model

Abstract

The volume of extensible markup language (XML) format documents is increasing every day due to the development of internet and the use of XML format in business process log file. Storing business process log data in XML format is preferable due to the ability of extensible and storing data irrespective of how it will be represented. However, mining XML format data poses challenges due to its complex data structure and dimensions. This paper proposes a method to convert XML format document into a structured format without ignoring the structural information. Converting semi-structured business process log data into structured format will allow more data mining techniques and statistical test be conducted and extract information from the business process log data. The experiment in this study performs t-test on a set of synthetic data and a set of real-world data to prove that information in business process log can be extracted through normal statistical test. Empirical results show that statistical analysis can be conducted on business process log data especially in XML format after flatten sequential structure model (FSSM) is used.