Case Study in Process Mining in a Multinational Enterprise

Abstract

Process mining has become an active area of research and while there are numerous papers on approaches to process mining there are fewer detailing its application to real industrial scenarios and its applicability in these spaces. In this paper we introduce the approach to process mining used in a number of multinational enterprises and then reflect upon the issues that have been encountered during our ongoing work. In our opinion these issues are a clear example of the challenges that need to be addressed during business process discovery from heterogeneous data.

A Lightweight RDF Data Model for Business Process Analysis

“…This is the case of many business process mining tools, such as Aperture [3], ProM [1] and Aris [7].…”

“…Next generation Business Intelligence (BI) systems will need to react to real-time events and predict the process behaviour in order to take corrective actions [10]. Moreover it is necessary to separate the data creation step from the analytical one in terms of meta-data dependency: departments that execute the processes are mostly unaware of the type of analysis that will be performed and they tend not to communicate small changes in the way and quantity of data they capture [3]. On the other side, also the analytical applications do not need to know how the information is captured, as long as it is made available on time and is compliant to a standard representation.…”

“…It has been developed from a set of recurrent requirements gathered with the experience our team developed from down-streaming of the business process mining tool [3]. These requirements were focused on a more flexible visualisation of the process workflow and the possibility to monitor real time process executions.…”

“…-by automatically extracting process models from existing systems logs, event logs, database transactions, audit trail events or other sources of information [1,2]; -by allowing instant analysis of the business processes using interactive visual displays of the process workflow; -by identifying specific case characteristics or trends that influence processing times [3].…”

“…The current technology typically requires the translation or import of data into the system before it can be analysed [1,2,3]. This imposes severe constraints on the way the data is represented and collected.…”