Handling Concept Drift for Predictions in Business Process Mining
This addresses the challenge of maintaining prediction quality in business process mining under changing data streams, though it is incremental as it focuses on data selection within existing retraining methods.
The paper tackles the problem of concept drift in business process mining by analyzing data selection strategies for model retraining, improving prediction accuracy from 0.5400 to 0.7010.
Predictive services nowadays play an important role across all business sectors. However, deployed machine learning models are challenged by changing data streams over time which is described as concept drift. Prediction quality of models can be largely influenced by this phenomenon. Therefore, concept drift is usually handled by retraining of the model. However, current research lacks a recommendation which data should be selected for the retraining of the machine learning model. Therefore, we systematically analyze different data selection strategies in this work. Subsequently, we instantiate our findings on a use case in process mining which is strongly affected by concept drift. We can show that we can improve accuracy from 0.5400 to 0.7010 with concept drift handling. Furthermore, we depict the effects of the different data selection strategies.