Predictive Process Monitoring related to the remaining time dimension: a value-driven framework

Nowadays, Big data promises automated actionable knowledge creation and predictive models for use by humans and computers. Therefore, one of the principal responsibilities of a data scientist is to make reliable predictions based on data, particularly, when the amount of available data is enormous. To do so, it is useful if some of the analysis can be automated and used process mining techniques.In this context, the ability to know in advance the trend of running process instances, with respect to different features, such as the expected completion time, would allow business managers to timely counteract to undesired situations, in order to prevent losses. Therefore, the techniques focus on predicting the remaining time influence other predictive process monitoring dimensions like: cost, delays, etc, i.e., predicting the remaining time, to accomplish an activity, helps respectively to predict the suitable resource and the next executing probable event. Indeed, a considerable number of methods have been put forward to address this prediction remaining time problem. However, none of the existing works have been grouped these methods (published from 2006 to 2019) in a framework.Therefore, the main objective of this paper is developing a value-driven framework for classifying existing work on predictive process monitoring, related to the remaining time dimension.This framework can support organizations to navigate in this predictive process monitoring specification field and help them to find value and exploit the opportunities enabled by these analysis techniques. This objective is achieved by systematically identifying, categorizing, and analyzing existing approaches for predictive process monitoring.