Evaluating early predictive performance of machine learning approaches for engineering change schedule – A case study using predictive process monitoring techniques

By applying machine learning algorithms, predictive business process monitoring (PBPM) techniques provide an opportunity to counteract undesired outcomes of processes. An especially complex variation of business processes is the engineering change (EC) process. Here, failing to adhere to planned imp...

Full description

Saved in:
Bibliographic Details
Main Authors: Ognjen Radišić-Aberger, Peter Burggräf, Fabian Steinberg, Alexander Becher, Tim Weißer
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Supply Chain Analytics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S294986352400030X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846138068778614784
author Ognjen Radišić-Aberger
Peter Burggräf
Fabian Steinberg
Alexander Becher
Tim Weißer
author_facet Ognjen Radišić-Aberger
Peter Burggräf
Fabian Steinberg
Alexander Becher
Tim Weißer
author_sort Ognjen Radišić-Aberger
collection DOAJ
description By applying machine learning algorithms, predictive business process monitoring (PBPM) techniques provide an opportunity to counteract undesired outcomes of processes. An especially complex variation of business processes is the engineering change (EC) process. Here, failing to adhere to planned implementation dates can have severe impacts on assembly lines, and it is paramount that potential negative cases are identified as early as possible. Current PBPM research, however, has seldomly investigated the predictive performance of machine learning approaches and their applicability at early process steps, let alone for the EC process. In our research, we show that given adequate feature encoding, shallow learners can accurately predict schedule adherence after process initialisation. Based on EC data from an automotive manufacturer, we provide a case sensitive performance overview on algorithm-encoding combinations. For that, three algorithms (XGBoost, Random Forest, LSTM) were combined with four encoding techniques. The encoding techniques used were the two common aggregation-based and index-based last state encoding, and two new combinations of these, which we term advanced aggregation-based and complex aggregation-based encoding. The study indicates that XGBoost-index-encoded approaches outclass regarding average predictive performance, whereas Random-Forest-aggregation-encoded approaches perform better regarding temporal stability due to reduced influence by dynamic features. Our research provides a case-based reasoning approach for deciding on which algorithm-encoding combination and evaluation metrics to apply. In doing so, we provide a blueprint for an early warning and monitoring method within the EC process and other similarly complex processes.
format Article
id doaj-art-005aaabe4cd54f3f988e1de6c900ecff
institution Kabale University
issn 2949-8635
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Supply Chain Analytics
spelling doaj-art-005aaabe4cd54f3f988e1de6c900ecff2024-12-07T08:35:25ZengElsevierSupply Chain Analytics2949-86352024-12-018100087Evaluating early predictive performance of machine learning approaches for engineering change schedule – A case study using predictive process monitoring techniquesOgnjen Radišić-Aberger0Peter Burggräf1Fabian Steinberg2Alexander Becher3Tim Weißer4Corresponding author.; Chair of International Production Engineering and Management (IPEM), Universität Siegen, Paul-Bonatz-Straße 9-11, Siegen 57076, GermanyChair of International Production Engineering and Management (IPEM), Universität Siegen, Paul-Bonatz-Straße 9-11, Siegen 57076, GermanyChair of International Production Engineering and Management (IPEM), Universität Siegen, Paul-Bonatz-Straße 9-11, Siegen 57076, GermanyChair of International Production Engineering and Management (IPEM), Universität Siegen, Paul-Bonatz-Straße 9-11, Siegen 57076, GermanyChair of International Production Engineering and Management (IPEM), Universität Siegen, Paul-Bonatz-Straße 9-11, Siegen 57076, GermanyBy applying machine learning algorithms, predictive business process monitoring (PBPM) techniques provide an opportunity to counteract undesired outcomes of processes. An especially complex variation of business processes is the engineering change (EC) process. Here, failing to adhere to planned implementation dates can have severe impacts on assembly lines, and it is paramount that potential negative cases are identified as early as possible. Current PBPM research, however, has seldomly investigated the predictive performance of machine learning approaches and their applicability at early process steps, let alone for the EC process. In our research, we show that given adequate feature encoding, shallow learners can accurately predict schedule adherence after process initialisation. Based on EC data from an automotive manufacturer, we provide a case sensitive performance overview on algorithm-encoding combinations. For that, three algorithms (XGBoost, Random Forest, LSTM) were combined with four encoding techniques. The encoding techniques used were the two common aggregation-based and index-based last state encoding, and two new combinations of these, which we term advanced aggregation-based and complex aggregation-based encoding. The study indicates that XGBoost-index-encoded approaches outclass regarding average predictive performance, whereas Random-Forest-aggregation-encoded approaches perform better regarding temporal stability due to reduced influence by dynamic features. Our research provides a case-based reasoning approach for deciding on which algorithm-encoding combination and evaluation metrics to apply. In doing so, we provide a blueprint for an early warning and monitoring method within the EC process and other similarly complex processes.http://www.sciencedirect.com/science/article/pii/S294986352400030XEngineering ChangeMachine LearningEffectivity DatePredictive Process MonitoringEarliness
spellingShingle Ognjen Radišić-Aberger
Peter Burggräf
Fabian Steinberg
Alexander Becher
Tim Weißer
Evaluating early predictive performance of machine learning approaches for engineering change schedule – A case study using predictive process monitoring techniques
Supply Chain Analytics
Engineering Change
Machine Learning
Effectivity Date
Predictive Process Monitoring
Earliness
title Evaluating early predictive performance of machine learning approaches for engineering change schedule – A case study using predictive process monitoring techniques
title_full Evaluating early predictive performance of machine learning approaches for engineering change schedule – A case study using predictive process monitoring techniques
title_fullStr Evaluating early predictive performance of machine learning approaches for engineering change schedule – A case study using predictive process monitoring techniques
title_full_unstemmed Evaluating early predictive performance of machine learning approaches for engineering change schedule – A case study using predictive process monitoring techniques
title_short Evaluating early predictive performance of machine learning approaches for engineering change schedule – A case study using predictive process monitoring techniques
title_sort evaluating early predictive performance of machine learning approaches for engineering change schedule a case study using predictive process monitoring techniques
topic Engineering Change
Machine Learning
Effectivity Date
Predictive Process Monitoring
Earliness
url http://www.sciencedirect.com/science/article/pii/S294986352400030X
work_keys_str_mv AT ognjenradisicaberger evaluatingearlypredictiveperformanceofmachinelearningapproachesforengineeringchangescheduleacasestudyusingpredictiveprocessmonitoringtechniques
AT peterburggraf evaluatingearlypredictiveperformanceofmachinelearningapproachesforengineeringchangescheduleacasestudyusingpredictiveprocessmonitoringtechniques
AT fabiansteinberg evaluatingearlypredictiveperformanceofmachinelearningapproachesforengineeringchangescheduleacasestudyusingpredictiveprocessmonitoringtechniques
AT alexanderbecher evaluatingearlypredictiveperformanceofmachinelearningapproachesforengineeringchangescheduleacasestudyusingpredictiveprocessmonitoringtechniques
AT timweißer evaluatingearlypredictiveperformanceofmachinelearningapproachesforengineeringchangescheduleacasestudyusingpredictiveprocessmonitoringtechniques