A branch of predictive analysis that attempts to predict some future state of a business process.
First, we show that LSTMs outperform existing techniques to predict the next event of a running case and its timestamp.
Predictive process monitoring aims to predict future characteristics of an ongoing process case, such as case outcome or remaining timestamp.
Predictive business process monitoring refers to the act of making predictions about the future state of ongoing cases of a business process, based on their incomplete execution traces and logs of historical (completed) traces.
Predictive process monitoring is a family of techniques to analyze events produced during the execution of a business process in order to predict the future state or the final outcome of running process instances.
We then show that temporal stability can be enhanced by hyperparameter-optimizing random forests and XGBoost classifiers with respect to inter-run stability.
Current explainable machine learning methods, such as LIME and SHAP, can be used to interpret black box models.