Forecasting Liquidated Damages via Machine Learning-Based Modified Regression Models for Highway Construction Projects

Abstract

Sustainable construction projects are essential for economic and societal thriving in modern communities. However, infrastructural construction is usually accompanied by delays in project delivery, which impact sustainability. Such delays adversely affect project time, cost, quality, safety objective functions, and associated Liquidated Damages (LDs). LDs are monetary charges to recompense the owner for additional expenses sustained if the project was not delivered on time due to delays caused by the contractor. This paper proposes modified regression modeling using machine learning (ML) techniques to develop solutions to the problem of predicting LDs for construction projects. The novel modeling methodology presented here is based on six years of data collection from many construction projects across the United States. It represents an innovative use of Multiple Linear Regression (MLR) models hybridized with machine learning (ML). The proposed methodology is evaluated using real datasets, where the developed model is designed to outperform the state-of-the-art LD forecast accuracy. Herein, seven modified regression-based models showed high accuracy in predicting the LDs. Nevertheless, those models’ forecasting ability was limited, so another second-order prediction model is proposed to provide better LD estimations. Independent variables were categorized based on their influence on the estimated LDs. The Total Bid Amount variable had the highest impact, while the Funding Indicator variable had a minimal impact. LD prediction was negatively correlated with all change-order-related variables and Total Adjustment Days, which suggests that those variables introduce extreme uncertainties due to their complex nature. The developed prediction models help decision-makers make better LDs predictions, which is essential for construction project sustainability.

Optimization of the Structural Performance of Buried Reinforced Concrete Pipelines in Cohesionless Soils

“…As a result, regardless of the pipe diameter, the optimal pipe thickness rose (nearly doubles) as the soil depth increases from 2.4 m to 20 m. This example shows how designers and practitioners utilize Equation (1) to determine the best reinforced concrete pipeline for a given pipe geometry and soil depth. Thus, in construction projects, providing decision-support tools using machine and deep learning approaches is vital [37][38][39][40][41][42][43][44][45][46][47][48].…”

A web-based system to determine risk of investment in international rail construction projects

“…The Monte Carlo simulation is a new way to assess the investment risk effects of international rail construction projects and is based on the probability distributions of the characteristics of data fluctuations in the past decade 1 . Although these SOTA models can evaluate the investment risk of international construction projects 17 , 18 , they can’t deal with multisource information immediately and they must process some of the data manually.…”

Analysis of Factors Affecting the Success of Sustainable Development Projects with the Help of Machine Learning Tools

“…Project success factors are components that must go well to guarantee the manager and organization's success [13]. In a study by Nguyen et al, five key success factors were extracted from 20 factors, which included competent project manager, providing sufficient financial resources until the end of the project, competent and multi-disciplinary project team, commitment to the project, and access to resources [28][29][30]. Evidently, there is a connection between project quality and project performance.…”

“…erefore, it will be difficult to evaluate model predictions. Accordingly, it can be learned that machine learning concepts are a good way to understand the performance and success of a project [29]. Project delay is one of the most important challenges of construction, which is attributed to the complexity of the sector and the interdependence of its inherently delayed risk sources.…”