KNNI-SVM: A hybrid algorithm integrating imputation and support vector machine for real-time business process monitoring

Abstract

Inductive data mining based approaches to process monitoring aim at investigating historical process logs and classifying the result of executed process. However, they show some limitations when applied to real-time monitoring such as late warnings or no real-time feedback capabilities. In order to alleviate such limitations, we propose a novel approach to real-time business process monitoring using a hybrid algorithm integrating support vector machine with k nearest neighbor imputation. By the proposed algorithm, an ongoing process instance is monitored through generated attributes and the final result of the instance is predicted based on them, which is iterated periodically as the ongoing instance progresses. Therefore, we can predict probable outcomes probabilistically based on the current progress. © 2011 ISSN 1881-803X.