Text-Aware Predictive Monitoring of Business Processes with LSTM Neural Networks
MSc Thesis Project
Title: Text-Aware Predictive Monitoring of Business Processes with LSTM Neural Networks
Supervisors: Marco Pegoraro, Dr.-Ing. Merih Seran Uysal
Examiner: Prof. Dr. Wil M.P. van der Aalst
2nd Examiner: Prof. Dr-Ing. Ulrik Schroeder
The real-time prediction of business processes using event data of historical executions is a critical capability of business process monitoring systems. Existing process prediction methods are limited in terms of the type of data they are able to utilize and the prediction tasks they can perform. In particular, almost no technique is able to utilize text documents of natural language, which can hold process-critical information. This work describes the design, implementation, and evaluation of a novel text-aware process prediction model based on long short-term memory (LSTM) neural networks and natural language mod- els. The proposed model can take categorical, numerical and textual attributes in event data into account to predict the activity and timestamp of the next event, the outcome, and the cycle time of a running process instance. Experiments show that the text-aware model is able to outperform state-of-the-art process prediction methods on simulated and real-world event logs containing textual data.
Keywords: Predictive Process Monitoring, Process Mining, Text Mining, LSTM Neural Networks