A Vector-Based Classification Approach for Remaining Time Prediction in Business Processes

TítuloA Vector-Based Classification Approach for Remaining Time Prediction in Business Processes
AutoresAhmad Aburomman, Manuel Lama, Alberto Bugarín
TipoArtículo de revista
Fonte IEEE Access, IEEE, 2019.
RankProvisionally ranked Q1 in Computer Science (all) by SJR 2018
ISSN2169-3536
DOI10.1109/ACCESS.2019.2939631
AbstractIn this paper, we deal with one of the current challenges in process mining enhancement: the prediction of remaining times in business processes. Accurate predictions of the remaining time, defined as the required time for an instance process to finish, are critical in many systems for organisations being able to establish a priori requirements, for optimal management of resources or for improving the quality of the services organisations provide. Our approach consists of i) extracting and assessing a number of features on the business logs, that provide a structural characterisation of the traces; ii) extending the well-known annotated transition system (ATS) model to include these features; and iii) applying a linear regression technique for predicting the remaining time of the traces for each state and features combinations. Extensive experimentation using eight attributes and ten real-life datasets show that the proposed approach outperforms in terms of mean absolute error and accuracy all the other approaches in state of the art, which includes ATS-based, non-ATS based as well as Deep Learning-based approaches.
Palabras chaveBusiness Processes Enhancement, Predictive Business Process monitoring, Business Processes Management, Business Intelligence