# Handling Concept Drift for Predictions in Business Process Mining

arXiv: https://arxiv.org/abs/2005.05810 · HTML: https://mlsanity.com/paper/2005.05810/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 May 2020.

## Built on by (most cited first, 7 of 7)

- [Machine learning in business process management: A systematic literature review](https://mlsanity.com/paper/2405.16396/) (2024)
- [Tailoring Machine Learning for Process Mining](https://mlsanity.com/paper/2306.10341/) (2023)
- [Machine Learning for QoS Prediction in Vehicular Communication: Challenges and Solution Approaches](https://mlsanity.com/paper/2302.11966/) (2023)
- [Targeted aspect-based emotion analysis to detect opportunities and precaution in financial Twitter messages](https://mlsanity.com/paper/2404.08665/) (2024)
- [ProcK: Machine Learning for Knowledge-Intensive Processes](https://mlsanity.com/paper/2109.04881/) (2021)
- [Measuring the Stability of Process Outcome Predictions in Online Settings](https://mlsanity.com/paper/2310.09000/) (2023)
- [StreamEnsemble: Predictive Queries over Spatiotemporal Streaming Data](https://mlsanity.com/paper/2410.00933/) (2024)

## Abstract (arXiv)

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.