Detection and In-Depth Analysis of Causes of Delay in Construction Projects: Synergy between Machine Learning and Expert Knowledge
Само за регистроване кориснике
2022
Аутори
Ivanović, MarijaNedeljković, Đorđe
Stojadinović, Zoran
Marinković, Dejan
Ivanišević, Nenad
Simić, Nevena
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
Due to numerous reasons, construction projects often fail to achieve the planned duration. Detecting causes of delays (CoD) is the first step in eliminating or mitigating potential delays in future projects. The goal of research is unbiased CoD detection at a single project level, with the ultimate goal to discover the root causes of delay. The existing approach is based on expert knowledge which is used to create CoD lists for projects in general or groups of similar projects. When applied to a single project, it is burdened with bias, as shown on a case project returning low Spearman Rank correlation values. This research introduces a Delay Root causes Extraction and Analysis Model—DREAM. The proposed model combines expert knowledge, machine learning techniques, and Minutes of Meetings (MoM) as an unutilized extensive source of information. In the first phase, DREAM outputs a CoD list based on occurring frequency in MoM with satisfactory recall values, significantly reducing expert-i...nduced subjectivism. In the second phase, enabled by MoM dates, DREAM adds another dimension to delay analysis—temporal CoD distribution. By analyzing corresponding informative charts, experts can understand the nature of delays and discover the root CoD, allowing intelligent decision making on future projects.
Кључне речи:
causes of delay / machine learning / transformers / bias / Spearman rank correlation / construction projectsИзвор:
Sustainability, 2022, 24Колекције
Институција/група
GraFarTY - JOUR AU - Ivanović, Marija AU - Nedeljković, Đorđe AU - Stojadinović, Zoran AU - Marinković, Dejan AU - Ivanišević, Nenad AU - Simić, Nevena PY - 2022 UR - https://grafar.grf.bg.ac.rs/handle/123456789/2958 AB - Due to numerous reasons, construction projects often fail to achieve the planned duration. Detecting causes of delays (CoD) is the first step in eliminating or mitigating potential delays in future projects. The goal of research is unbiased CoD detection at a single project level, with the ultimate goal to discover the root causes of delay. The existing approach is based on expert knowledge which is used to create CoD lists for projects in general or groups of similar projects. When applied to a single project, it is burdened with bias, as shown on a case project returning low Spearman Rank correlation values. This research introduces a Delay Root causes Extraction and Analysis Model—DREAM. The proposed model combines expert knowledge, machine learning techniques, and Minutes of Meetings (MoM) as an unutilized extensive source of information. In the first phase, DREAM outputs a CoD list based on occurring frequency in MoM with satisfactory recall values, significantly reducing expert-induced subjectivism. In the second phase, enabled by MoM dates, DREAM adds another dimension to delay analysis—temporal CoD distribution. By analyzing corresponding informative charts, experts can understand the nature of delays and discover the root CoD, allowing intelligent decision making on future projects. T2 - Sustainability T1 - Detection and In-Depth Analysis of Causes of Delay in Construction Projects: Synergy between Machine Learning and Expert Knowledge VL - 24 DO - 10.3390/su142214927 ER -
@article{ author = "Ivanović, Marija and Nedeljković, Đorđe and Stojadinović, Zoran and Marinković, Dejan and Ivanišević, Nenad and Simić, Nevena", year = "2022", abstract = "Due to numerous reasons, construction projects often fail to achieve the planned duration. Detecting causes of delays (CoD) is the first step in eliminating or mitigating potential delays in future projects. The goal of research is unbiased CoD detection at a single project level, with the ultimate goal to discover the root causes of delay. The existing approach is based on expert knowledge which is used to create CoD lists for projects in general or groups of similar projects. When applied to a single project, it is burdened with bias, as shown on a case project returning low Spearman Rank correlation values. This research introduces a Delay Root causes Extraction and Analysis Model—DREAM. The proposed model combines expert knowledge, machine learning techniques, and Minutes of Meetings (MoM) as an unutilized extensive source of information. In the first phase, DREAM outputs a CoD list based on occurring frequency in MoM with satisfactory recall values, significantly reducing expert-induced subjectivism. In the second phase, enabled by MoM dates, DREAM adds another dimension to delay analysis—temporal CoD distribution. By analyzing corresponding informative charts, experts can understand the nature of delays and discover the root CoD, allowing intelligent decision making on future projects.", journal = "Sustainability", title = "Detection and In-Depth Analysis of Causes of Delay in Construction Projects: Synergy between Machine Learning and Expert Knowledge", volume = "24", doi = "10.3390/su142214927" }
Ivanović, M., Nedeljković, Đ., Stojadinović, Z., Marinković, D., Ivanišević, N.,& Simić, N.. (2022). Detection and In-Depth Analysis of Causes of Delay in Construction Projects: Synergy between Machine Learning and Expert Knowledge. in Sustainability, 24. https://doi.org/10.3390/su142214927
Ivanović M, Nedeljković Đ, Stojadinović Z, Marinković D, Ivanišević N, Simić N. Detection and In-Depth Analysis of Causes of Delay in Construction Projects: Synergy between Machine Learning and Expert Knowledge. in Sustainability. 2022;24. doi:10.3390/su142214927 .
Ivanović, Marija, Nedeljković, Đorđe, Stojadinović, Zoran, Marinković, Dejan, Ivanišević, Nenad, Simić, Nevena, "Detection and In-Depth Analysis of Causes of Delay in Construction Projects: Synergy between Machine Learning and Expert Knowledge" in Sustainability, 24 (2022), https://doi.org/10.3390/su142214927 . .