Predictive Process Mining for Business Process Management Improvement (Extended Abstract)

Predictive Process Mining (PPM) has a strategic role in decision-making and managerial contexts of a company since it allows the prediction in advance of the evolution of process instances (traces). Although various PPM algorithms have been proposed in the recent process mining literature, the emergence of machine learning has brought new solutions that still demand for investigation, in order to set new milestones by combining process mining techniques with (deep) machine learning methods. The main goal of this thesis is to explore the potential of such a combination by proposing different novel methods that take advantage of the integration between process mining and machine learning. This integration is explored by handling volume, variety, variability and/or value dimensions of event data.