Disputes Using Machine Learning Techniques Classifying Compensations in Construction

Date

2023-03-01

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

111
views

134
downloads

Cite This

It is highly probable to encounter disputes in construction projects and construction disputes are detrimental as they may lead to cost overruns and delays. Knowing the compensation with some certainty can avoid parties from extending inconclusive claims. Decision support systems can be helpful to understand the aspect of the compensation, if any compensation can be acquired. Within this context, the primary objective of this research is to predict the associated compensations in construction disputes by using machine learning (ML) techniques on past project data so that in new projects, decision support can be provided with some certainty via forecasts on the aspect of the compensation. To do this, a conceptual model identifying the attributes affecting compensations was established based on an extensive literature review. Using these attributes, data from real-world dispute cases were collected. Insignificant attributes were eliminated via Chi-square tests to establish a simpler classification model, which was experimented via alternative single and ensemble ML techniques. The Naïve Bayes (NB) classifier generated the highest average classification accuracy as 80.61% when One-vs-All (OvA) decomposition technique was utilized. The conceptual model can guide construction professionals during dispute management decision-making and the promising results indicate that the classification model has the potential to identify compensations. This study can be used to mitigate disputes by preventing parties from resorting to unpleasant and inconclusive resolution processes.

Subject Keywords

Compensation, Construction disputes, Data classification, Dispute management, Machine learning

URI

https://hdl.handle.net/11511/103533

Collections

Department of Civil Engineering, Article