Evaluating Predictive Business Process Monitoring Approaches on Small Event Logs

Abstract

Predictive business process monitoring is concerned with the prediction how a running process instance will unfold up to its completion at runtime. Most of the proposed approaches rely on a wide number of machine learning techniques. In the last years numerous studies revealed that these methods can be successfully applied for different prediction targets. However, these techniques require a qualitatively and quantitatively sufficient dataset. Unfortunately, there are many situations in business process management where only a quantitatively insufficient dataset is available. The problem of insufficient data in the context of BPM is still neglected. Hence, none of the comparative studies investigates the performance of predictive business process monitoring techniques in environments with small datasets. In this paper an evaluation framework for comparing existing approaches with regard to their suitability for small datasets is developed and exemplarily applied to state-of-the-art approaches in next activity prediction.