Performance-Preserving Event Log Sampling for Predictive Monitoring
This work addresses the problem of slow and infeasible training in predictive monitoring for process stakeholders, offering an incremental improvement to existing methods.
The paper tackles the inefficiency of training complex machine learning models for predictive process monitoring by proposing an instance selection procedure for sampling training data, resulting in a significant increase in training speed while maintaining reliable prediction accuracy for next activity and remaining time predictions.
Predictive process monitoring is a subfield of process mining that aims to estimate case or event features for running process instances. Such predictions are of significant interest to the process stakeholders. However, most of the state-of-the-art methods for predictive monitoring require the training of complex machine learning models, which is often inefficient. Moreover, most of these methods require a hyper-parameter optimization that requires several repetitions of the training process which is not feasible in many real-life applications. In this paper, we propose an instance selection procedure that allows sampling training process instances for prediction models. We show that our instance selection procedure allows for a significant increase of training speed for next activity and remaining time prediction methods while maintaining reliable levels of prediction accuracy.