How do I update my model? On the resilience of Predictive Process Monitoring models to change

TL;DR

This paper investigates the resilience of Predictive Process Monitoring models to process changes by evaluating incremental learning strategies that update models with new data, enhancing adaptability in evolving environments.

Contribution

It introduces and evaluates three strategies for updating predictive models in process monitoring, addressing the rigidity of static models in dynamic settings.

Findings

Incremental learning improves model accuracy over time.

Updated models adapt better to concept drift.

Incremental strategies are computationally feasible.

Abstract

Existing well investigated Predictive Process Monitoring techniques typically construct a predictive model based on past process executions, and then use it to predict the future of new ongoing cases, without the possibility of updating it with new cases when they complete their execution. This can make Predictive Process Monitoring too rigid to deal with the variability of processes working in real environments that continuously evolve and/or exhibit new variant behaviours over time. As a solution to this problem, we evaluate the use of three different strategies that allow the periodic rediscovery or incremental construction of the predictive model so as to exploit new available data. The evaluation focuses on the performance of the new learned predictive models, in terms of accuracy and time, against the original one, and uses a number of real and synthetic datasets with and without explicit Concept Drift. The results provide an evidence of the potential of incremental learning algorithms for predicting process monitoring in real environments.