Prediction Liquidated Damages via Ensemble Machine Learning Model: Towards Sustainable Highway Construction Projects: Fid-Bau Portal

Prediction Liquidated Damages via Ensemble Machine Learning Model: Towards Sustainable Highway Construction Projects

Odey Alshboul / Ali Shehadeh / Rabia Emhamed Al Mamlook / Ghassan Almasabha / Ali Saeed Almuflih / Saleh Y. Alghamdi

Highway construction projects are important for financial and social development in the United States. Such types of construction are usually accompanied by construction delay, causing liquidated damages ( $L D s$ ) as a contractual provision are vital in construction agreements. Accurate quantification of $L D s$ is essential for contract parties to avoid legal disputes and unfair provisions due to the lack of appropriate documentation. This paper effort sought to develop an ensemble machine learning technique ( $E M L T$ ) that combines algorithms of the Extreme Gradient Boosting ( $X G B o o s t)$ , Categorical Boosting ( $C a t B o o s t$ ), k-Nearest Neighbor ( $k N N$ ), Light Gradient Boosting Machine ( $L i g h t G B M$ ), Artificial Neural Network ( $A N N$ ), and Decision Tree ( $D T$ ) for the prediction of $L D s$ in highway construction projects. Key attributes are identified and examined to predict the interrelated correlations among the influential features to develop accurate forecast models to assess the impact of each delay factor. Various machine-learning-based models were developed, where the different modeling outputs were analyzed and compared. Four performance matrices such as Root Mean Square Error ( $R M S E$ ), Mean Absolute Error ( $M A E$ ), Mean Absolute Percentage Error ( $M A P E$ ), and Coefficient of Determination ( $R^{2}$ ) were used to assess and evaluate the accuracy of the implemented machine learning ( $M L$ ) algorithms. The prediction outputs implied that the developed EMLT model has shown better performance compared to other ML-based models, where it has the highest accuracy of 0.997, compared to the DT, kNN, CatBoost, XGBoost, LightGBM, and ANN with an accuracy of 0.989, 0.988, 0.986, 0.975, 0.873, and 0.689, respectively. Thus, the findings of this research designate that the EMLT model can be used as an effective administrative decision adding tool for forecasting the $L D s$ . As a result, this paper emphasizes ML’s potential to aid in the advancement of computerization as a comprehensible subject of investigation within highway building projects.