Parallel-Structure Deep Learning for Prediction of Remaining Time of Process Instances

Event logs generated by Process-Aware Information Systems (PAIS) provide many opportunities for analysis that are expected to help organizations optimize their business processes. The ability to monitor business processes proactively can allow an organization to achieve, maintain or enhance competit...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Nur Ahmad Wahid, Hyerim Bae, Taufik Nur Adi, Yulim Choi, Yelita Anggiane Iskandar
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	predictive business process monitoring deep learning convolutional neural network embedding layer remaining time prediction Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/c6cfaf8323724a16a6b6764029f4a06b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c6cfaf8323724a16a6b6764029f4a06b
record_format	dspace
spelling	oai:doaj.org-article:c6cfaf8323724a16a6b6764029f4a06b2021-11-11T14:58:54ZParallel-Structure Deep Learning for Prediction of Remaining Time of Process Instances10.3390/app112198482076-3417https://doaj.org/article/c6cfaf8323724a16a6b6764029f4a06b2021-10-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/9848https://doaj.org/toc/2076-3417Event logs generated by Process-Aware Information Systems (PAIS) provide many opportunities for analysis that are expected to help organizations optimize their business processes. The ability to monitor business processes proactively can allow an organization to achieve, maintain or enhance competitiveness in the market. Predictive Business Process Monitoring (PBPM) can provide measures such as the prediction of the remaining time of an ongoing process instance (case) by taking past activities in running process instances into account, as based on the event logs of previously completed process instances. With the prediction provided, we expect that organizations can respond quickly to deviations from the desired process. In the context of the growing popularity of deep learning and the need to utilize heterogeneous representation of data; in this study, we derived a new deep-learning approach that utilizes two types of data representation based on a parallel-structure model, which consists of a convolutional neural network (CNN) and a multi-layer perceptron (MLP) with an embedding layer, to predict the remaining time. Conducting experiments with real-world datasets, we compared our proposed method against the existing deep-learning approach to confirm its utility for the provision of more precise prediction (as indicated by error metrics) relative to the baseline method.Nur Ahmad WahidHyerim BaeTaufik Nur AdiYulim ChoiYelita Anggiane IskandarMDPI AGarticlepredictive business process monitoringdeep learningconvolutional neural networkembedding layerremaining time predictionTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 9848, p 9848 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	predictive business process monitoring deep learning convolutional neural network embedding layer remaining time prediction Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	predictive business process monitoring deep learning convolutional neural network embedding layer remaining time prediction Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Nur Ahmad Wahid Hyerim Bae Taufik Nur Adi Yulim Choi Yelita Anggiane Iskandar Parallel-Structure Deep Learning for Prediction of Remaining Time of Process Instances
description	Event logs generated by Process-Aware Information Systems (PAIS) provide many opportunities for analysis that are expected to help organizations optimize their business processes. The ability to monitor business processes proactively can allow an organization to achieve, maintain or enhance competitiveness in the market. Predictive Business Process Monitoring (PBPM) can provide measures such as the prediction of the remaining time of an ongoing process instance (case) by taking past activities in running process instances into account, as based on the event logs of previously completed process instances. With the prediction provided, we expect that organizations can respond quickly to deviations from the desired process. In the context of the growing popularity of deep learning and the need to utilize heterogeneous representation of data; in this study, we derived a new deep-learning approach that utilizes two types of data representation based on a parallel-structure model, which consists of a convolutional neural network (CNN) and a multi-layer perceptron (MLP) with an embedding layer, to predict the remaining time. Conducting experiments with real-world datasets, we compared our proposed method against the existing deep-learning approach to confirm its utility for the provision of more precise prediction (as indicated by error metrics) relative to the baseline method.
format	article
author	Nur Ahmad Wahid Hyerim Bae Taufik Nur Adi Yulim Choi Yelita Anggiane Iskandar
author_facet	Nur Ahmad Wahid Hyerim Bae Taufik Nur Adi Yulim Choi Yelita Anggiane Iskandar
author_sort	Nur Ahmad Wahid
title	Parallel-Structure Deep Learning for Prediction of Remaining Time of Process Instances
title_short	Parallel-Structure Deep Learning for Prediction of Remaining Time of Process Instances
title_full	Parallel-Structure Deep Learning for Prediction of Remaining Time of Process Instances
title_fullStr	Parallel-Structure Deep Learning for Prediction of Remaining Time of Process Instances
title_full_unstemmed	Parallel-Structure Deep Learning for Prediction of Remaining Time of Process Instances
title_sort	parallel-structure deep learning for prediction of remaining time of process instances
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/c6cfaf8323724a16a6b6764029f4a06b
work_keys_str_mv	AT nurahmadwahid parallelstructuredeeplearningforpredictionofremainingtimeofprocessinstances AT hyerimbae parallelstructuredeeplearningforpredictionofremainingtimeofprocessinstances AT taufiknuradi parallelstructuredeeplearningforpredictionofremainingtimeofprocessinstances AT yulimchoi parallelstructuredeeplearningforpredictionofremainingtimeofprocessinstances AT yelitaanggianeiskandar parallelstructuredeeplearningforpredictionofremainingtimeofprocessinstances
_version_	1718437927155924992

Parallel-Structure Deep Learning for Prediction of Remaining Time of Process Instances

Ejemplares similares