On 29th of May, 2021, Lotte Vugs received the Dow Chemical Best OML Master Thesis Award 2020. The jury unanimously decided to grant the award to Lotte, which is accompanied by a check of 1,000 Euros. This yearly award is usually handed over by a representative of Dow at the Diploma Ceremony in Fall. This time, following delays and constraints because of Corona, the award was handed over at the Drive through Diploma Ceremony in Atlas, by the jury chair.
The jury consisted of Aram de Ruiter and Jeffrey Tazelaar from Dow Chemical, and Remco Dijkman and Tugce Martagan from Eindhoven University of Technology. Marco Slikker served as non-voting jury chair. The jury judged the theses on their academic contribution and industrial impact. The students that graduated in the past academic year and received at least a grade of 9 for their theses have been nominated for the award. 17 students satisfied this criterium, 7 of which were females. The jury concluded that all these 17 theses were of outstanding quality and well reflected the objectives of the Operations Management & Logistics program, i.e., to use formal models to analyze, improve, and redesign operational processes. Finding the right balance between academic impact and industrial application is always difficult, but the jury commends all candidates with finding this balance in an excellent way.
The thesis of Lotte, entitled “Process Mining for Semi-Structured Log Entries” is highly innovative. Where process mining based on structured event logs is a well-studied subject, process mining based on semi-structured event logs is not studied to the best of our knowledge. The challenge in semi-structured event logs is that tasks are described in natural language rather than by pre-defined task labels, which makes it hard to determine which descriptions represent the same tasks. The thesis provides a strong academic contribution to this area by: providing a conceptual model for process mining on semi-structured event logs, defining natural language processing techniques for identifying tasks according to this model, and creating an innovative combination of process mining and natural language processing to finally mine processes. A scientific paper based on the thesis is in progress.
The thesis explores an application considered to be very relevant in today’s industry as well. Frequently, process mining is done with the data in systems, both the data in process systems as well as ERP systems. Process mining is used for better understanding and thus improving business processes. This thesis works out the development of a system to extract information from semi-structured event logs and in that way complements the structured data already available in the systems. The work is innovative and describes actual results. Finally, the thesis is well written.