Predicting Remaining Cycle Time from Ongoing Cases: A Survival Analysis-Based Approach

Predicting the remaining cycle time of running cases is one important use case of predictive process monitoring. Different approaches that learn from event logs, e.g., relying on an existing representation of the process or leveraging machine learning approaches, have been pro posed in literature to...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Baskharon, Fadi (author)
مؤلفون آخرون: Awad, Ahmed (author), Di Francescomarino, Chiara (author)
منشور في: 2020
الموضوعات:
الوصول للمادة أونلاين:https://bspace.buid.ac.ae/handle/1234/2928
https://link.springer.com/chapter/10.1007/978-3-030-72693-5_8
https://doi.org/10.1007/978-3-030-72693-5_8
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1862980611659005952
author Baskharon, Fadi
author2 Awad, Ahmed
Di Francescomarino, Chiara
author2_role author
author
author_facet Baskharon, Fadi
Awad, Ahmed
Di Francescomarino, Chiara
author_role author
dc.creator.none.fl_str_mv Baskharon, Fadi
Awad, Ahmed
Di Francescomarino, Chiara
dc.date.none.fl_str_mv 2020
2025-05-06T08:54:40Z
2025-05-06T08:54:40Z
dc.identifier.none.fl_str_mv Baskharon, F., Awad, A., Di Francescomarino, C. (2021). Predicting Remaining Cycle Time from Ongoing Cases: A Survival Analysis-Based Approach. In: Leemans, S., Leopold, H. (eds) Process Mining Workshops. ICPM 2020. Lecture Notes in Business Information Processing, vol 406. Springer, Cham.
https://bspace.buid.ac.ae/handle/1234/2928
https://link.springer.com/chapter/10.1007/978-3-030-72693-5_8
https://doi.org/10.1007/978-3-030-72693-5_8
dc.language.none.fl_str_mv en
dc.publisher.none.fl_str_mv Springer, Cham
dc.relation.none.fl_str_mv Process Mining Workshops, 2021, Volume 406
dc.subject.none.fl_str_mv Predictive process monitoring · Remaining time prediction · Survival analysis · Incomplete traces
dc.title.none.fl_str_mv Predicting Remaining Cycle Time from Ongoing Cases: A Survival Analysis-Based Approach
dc.type.none.fl_str_mv Article
description Predicting the remaining cycle time of running cases is one important use case of predictive process monitoring. Different approaches that learn from event logs, e.g., relying on an existing representation of the process or leveraging machine learning approaches, have been pro posed in literature to tackle this problem. Machine learning-based tech niques have shown superiority over other techniques with respect to the accuracy of the prediction as well as freedom from knowledge about the underlying process models generating the logs. However, all proposed approaches learn from complete traces. This might cause delays in start ing new training cycles as usually process instances might last over long time periods of hours, days, weeks or even months. In this paper, we propose a machine learning approach that can learn from incomplete ongoing traces. Using a time-aware survival analysis technique, we can train a neural network to predict the remaining cycle time of a running case. Our approach accepts as input both complete and incomplete traces. We have evaluated our approach on different real-life datasets and compared it with a state of the art baseline. Results show that our approach, in many cases, is able to outperform the baseline approach both in accuracy and training time
id budr_21e745063ae1ade2fa3eeeb32582e9a2
identifier_str_mv Baskharon, F., Awad, A., Di Francescomarino, C. (2021). Predicting Remaining Cycle Time from Ongoing Cases: A Survival Analysis-Based Approach. In: Leemans, S., Leopold, H. (eds) Process Mining Workshops. ICPM 2020. Lecture Notes in Business Information Processing, vol 406. Springer, Cham.
language_invalid_str_mv en
network_acronym_str budr
network_name_str The British University in Dubai repository
oai_identifier_str oai:bspace.buid.ac.ae:1234/2928
publishDate 2020
publisher.none.fl_str_mv Springer, Cham
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Predicting Remaining Cycle Time from Ongoing Cases: A Survival Analysis-Based ApproachBaskharon, FadiAwad, AhmedDi Francescomarino, ChiaraPredictive process monitoring · Remaining time prediction · Survival analysis · Incomplete tracesPredicting the remaining cycle time of running cases is one important use case of predictive process monitoring. Different approaches that learn from event logs, e.g., relying on an existing representation of the process or leveraging machine learning approaches, have been pro posed in literature to tackle this problem. Machine learning-based tech niques have shown superiority over other techniques with respect to the accuracy of the prediction as well as freedom from knowledge about the underlying process models generating the logs. However, all proposed approaches learn from complete traces. This might cause delays in start ing new training cycles as usually process instances might last over long time periods of hours, days, weeks or even months. In this paper, we propose a machine learning approach that can learn from incomplete ongoing traces. Using a time-aware survival analysis technique, we can train a neural network to predict the remaining cycle time of a running case. Our approach accepts as input both complete and incomplete traces. We have evaluated our approach on different real-life datasets and compared it with a state of the art baseline. Results show that our approach, in many cases, is able to outperform the baseline approach both in accuracy and training timeSpringer, Cham2025-05-06T08:54:40Z2025-05-06T08:54:40Z2020ArticleBaskharon, F., Awad, A., Di Francescomarino, C. (2021). Predicting Remaining Cycle Time from Ongoing Cases: A Survival Analysis-Based Approach. In: Leemans, S., Leopold, H. (eds) Process Mining Workshops. ICPM 2020. Lecture Notes in Business Information Processing, vol 406. Springer, Cham.https://bspace.buid.ac.ae/handle/1234/2928https://link.springer.com/chapter/10.1007/978-3-030-72693-5_8https://doi.org/10.1007/978-3-030-72693-5_8enProcess Mining Workshops, 2021, Volume 406oai:bspace.buid.ac.ae:1234/29282025-08-13T09:26:45Z
spellingShingle Predicting Remaining Cycle Time from Ongoing Cases: A Survival Analysis-Based Approach
Baskharon, Fadi
Predictive process monitoring · Remaining time prediction · Survival analysis · Incomplete traces
title Predicting Remaining Cycle Time from Ongoing Cases: A Survival Analysis-Based Approach
title_full Predicting Remaining Cycle Time from Ongoing Cases: A Survival Analysis-Based Approach
title_fullStr Predicting Remaining Cycle Time from Ongoing Cases: A Survival Analysis-Based Approach
title_full_unstemmed Predicting Remaining Cycle Time from Ongoing Cases: A Survival Analysis-Based Approach
title_short Predicting Remaining Cycle Time from Ongoing Cases: A Survival Analysis-Based Approach
title_sort Predicting Remaining Cycle Time from Ongoing Cases: A Survival Analysis-Based Approach
topic Predictive process monitoring · Remaining time prediction · Survival analysis · Incomplete traces
url https://bspace.buid.ac.ae/handle/1234/2928
https://link.springer.com/chapter/10.1007/978-3-030-72693-5_8
https://doi.org/10.1007/978-3-030-72693-5_8