A ProM Operational Support Provider for Predictive Monitoring of Business Processes

Predictive process monitoring is concerned with exploiting event logs to predict how running (uncompleted) cases will unfold up to their completion. In this paper, we propose an implementation in the ProM toolset of a predictive process monitoring framework for estimating the probability that an ongoing case will lead to a certain outcome among a set of possible outcomes. An outcome refers to a label associated to completed cases, like, for example, a label indicating that a given case completed "on time" (with respect to a given desired duration) or "late", or a label indicating that a given case led to a customer complaint or not. The framework takes into account both the sequence of events observed in the current trace, as well as data attributes associated to these events. The prediction problem is approached in two phases. First, prefixes of previous traces are clustered according to control flow information. Secondly, a classifier is built for each cluster to discriminate among a...

Predictive process monitoring is concerned with exploiting event logs to predict how running (uncompleted) cases will unfold up to their completion. In this paper, we propose an implementation in the ProM toolset of a predictive process monitoring framework for estimating the probability that an ongoing case will lead to a certain outcome among a set of possible outcomes. An outcome refers to a label associated to completed cases, like, for example, a label indicating that a given case completed " on time " (with respect to a given desired duration) or " late " , or a label indicating that a given case led to a customer complaint or not. The framework takes into account both the sequence of events observed in the current trace, as well as data attributes associated to these events. The prediction problem is approached in two phases. First, prefixes of previous traces are clustered according to control flow information. Secondly , a classifier is built for each cluster to discriminate among a set of possible outcomes. At runtime, a prediction is made on a running case by mapping it to a cluster and applying the corresponding classifier.