Evaluating Predictive Business Process Monitoring Approaches on Small Event Logs

TL;DR

This paper evaluates how existing predictive business process monitoring methods perform when only small event logs are available, addressing a gap in current research that assumes larger datasets.

Contribution

It develops an evaluation framework specifically for assessing predictive approaches on small datasets and applies it to current state-of-the-art methods.

Findings

Identifies the performance gap of monitoring approaches with small data

Provides insights into the suitability of different methods for limited data scenarios

Highlights the need for tailored approaches in small data environments

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 different machine learning (ML) techniques. In the last years numerous comparative studies, reviews, and benchmarks of such approaches where published and revealed that they can be successfully applied for different prediction targets. ML techniques require a qualitatively and quantitatively sufficient data set. However, there are many situations in business process management (BPM) where only a quantitatively insufficient data set is available. The problem of insufficient data in the context of BPM is still neglected. Hence, none of the comparative studies or benchmarks investigates the performance of predictive business process monitoring techniques in environments with small data sets. In this paper an evaluation framework for comparing existing approaches with regard to their suitability for small data sets is developed and exemplarily applied to state-of-the-art approaches in predictive business process monitoring.