Comparing Performances of Machine Learning Techniques to Forecast Dispute Resolutions

Download

index.pdf

Date

2022-9-01

Author

AYHAN, MURAT
Dikmen Toker, İrem
Birgönül, Mustafa Talat

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

73
views

37
downloads

This paper compares classification performances of machine learning (ML) techniques for forecasting dispute resolutions in construction projects, thereby mitigating the impacts of potential disputes Findings revealed that resolution cost and duration, contractor type, dispute source, and occurrence of changes were the most influential factors on dispute resolution method (DRM) preferences. The promising accuracy of the majority voting classifier (89.44%) indicates that the proposed model can provide decision-support in identification of potential resolutions. Decision-makers can avoid unsatisfactory processes using these forecasts. This paper demonstrated the effectiveness of ML techniques in classification of DRMs, and the proposed prediction model outperformed previous studies.

Subject Keywords

Construction disputes, dispute resolution methods, multiclass classification, dispute management, ARTIFICIAL-INTELLIGENCE, CONSTRUCTION-INDUSTRY, NEURAL-NETWORK, PREDICTION, MODEL, KNOWLEDGE

URI

https://hdl.handle.net/11511/101081

Journal

TEKNIK DERGI

DOI

https://doi.org/10.18400/tekderg.930076

Collections

Department of Civil Engineering, Article

Suggestions

OpenMETU
Core

Causal mapping to explore emergence of construction disputes Tanriverdi, Cenk; Atasoy Özcan, Güzide; Dikmen Toker, İrem; Birgönül, Mustafa Talat (2021-05-24) Disputes, frequently encountered in construction projects, can substantially affect project success, necessitating a clear understanding of how and why disputes occur. Previous studies on disputes mostly yielded exhaustive lists or hierarchies of possible causes of disputes, which can hardly be used to understand how these causes come together to form a dispute. To address this gap, this study provides an alternative approach to understand the underlying causes of disputes, and their relationship within a s...
Comparison of the resource allocation cababilities of project management software packages in resource constrained project scheduling problems Hekimoğlu, Özge; Serpil, Canan; Department of Industrial Engineering (2007) In this study, results of a comparison on benchmark test problems are presented to investigate the performance of Primavera V.4.1 with its two resource allocation priority rules and MS Project 2003. Resource allocation capabilities of the packages are measured in terms of deviation from the upper bound of the minimum makespan. Resource constrained project scheduling problem instances are taken from PSPLIB which are generated under a factorial design from ProGen. Statistical tests are applied to the results ...
Development of dispute prediction and resolution method selection models for construction disputes Ayhan, Mura; Birgönül, Mustafa Talat; Department of Civil Engineering (2019) Construction industry is overwhelmed by increasing number and severity of disputes proving that current practices are insufficient in avoidance. This research argues that in order to forestall and mitigate construction disputes, prediction models should be developed by utilizing machine learning algorithms. The research suggests developing three distinct models; (1) dispute occurrence prediction model, (2) potential compensation prediction model, and (3) resolution method selection model. For this reason, a...
Development of a lessons learned management process model and a web-based tool for construction companies Eken, Görkem; Birgönül, Mustafa Talat; Dikmen Toker, İrem; Department of Civil Engineering (2017) Organizational memory formation and its effective utilization is a source of competitive advantage especially in project-based industries such as construction industry as it may eliminate potential problems in projects leading to higher profitability and less errors. However, project-based nature also poses challenges for establishing organizational memory as it is hard to capture knowledge of temporary project teams and transfer different types of knowledge between projects. This study presents a “Lessons ...
Comparison of response surface methodology and the proposed Weibull model for inactivation of Listeria innocua by high hydrostatic pressure BUZRUL, Sencer; CEVIK, Mete; Alpas, Hami (Wiley, 2008-02-01) Published inactivation data of Listeria innocua by high hydrostatic pressure (HHP) were used to compare the prediction capabilities of response surface methodology (RSM) and the proposed Weibull model. A quadratic function was used for the secondary modeling of the reduced Weibull model's time constant parameter so that this model consisted of pressure, temperature and time just like RSM equation. Application of each model was shown separately. The usability, differences and similarities of these models wer...

Citation Formats

M. AYHAN, İ. Dikmen Toker, and M. T. Birgönül, “Comparing Performances of Machine Learning Techniques to Forecast Dispute Resolutions,” TEKNIK DERGI, vol. 33, no. 5, pp. 12577–12600, 2022, Accessed: 00, 2022. [Online]. Available: https://hdl.handle.net/11511/101081.