Artificial Neural Network Model to Predict Final Construction Contract Duration

Abstract

Forecasting the final construction contract duration at an early stage plays a vital role in the progress of a project. An inaccurate project duration prediction may lead to the project’s benefits being lost. It is essential to precisely predict the duration due to the presence of several different factors. This paper contributed to developing a model to predict final construction contract duration (FCCD) in the early stages based on parameters characterized as few and shared for any contract. (contract cost, contract duration, and sector). This paper developed an Artificial Neural Network (ANN) model based on 135 Saudi construction project data. The development model has three stages. The first stage was standardization and augmentation using Zavadskas and Turskis’ logarithmic and Pasini methods. The second and third stages were the first and second analyses of the ANN models, respectively. The first analysis aimed to promote the used data and integrate them into the second analysis to develop the ANN model. The ANN models were compared with three linear regression (LR) models (LR1, LR2, and LR3) and other models in the literature. The results revealed that the accuracy of the ANN model provides reasonable accuracy with an average mean absolute percentage error (MAPE) of 12.22%, which is lower than the LR3′s MAPE by 27.03%. The accuracy of the ANN model is similar to that of earned value management (EVM) in the previous study. This paper supports research to deal with relatively little data and integrate them into a neural network. The ANN model assists the stakeholder in making appropriate decisions for the project during the pre-tendering phase by predicting the actual contract duration based on the CC, CD, and project sector.

Criticality-Based Management of Facility Assets

“…The application of an ANN and neuro-fuzzy for construction scheduling was studied by [31]. The authors in [32] predicted the construction contract duration for construction projects. An optimum scheduling model using an ANN was developed by the authors in [33].…”

Analyzing Contingency Estimation for Residential Turnkey Projects in Saudi Arabia: A Neural Network Approach

“…Artificial Neural Networks (ANNs) are increasingly utilized in the construction industry, capitalizing on their capabilities in pattern recognition, predictive modeling, and decision-making support. Numerous researchers have employed ANNs to estimate project costs and facilitate budget allocation [15][16][17][18][19][20][21][22][23], as well as to enhance project scheduling [24][25][26][27][28]. The process of designing, training, and using Artificial Neural Networks (ANNs) involves several key stages, each contributing to the network's ability to perform tasks such as classification, regression, prediction, and more.…”

Machine Learning Technologies in the Supply Chain Management Research of Biodiesel: A Review

“…Figure 5 illustrates the general modeling procedure of ANN consisting of experimental data collection, ANN modeling, and validation and statistical analysis between the simulated and experimental outputs [64]. Rocabruno-Valdes et al [63] utilized Matlab software (2015a) with a neural network toolbox for the ANN modeling, and they conducted sensitivity analysis on independent variables to identify the impact of independent variables on the response variables.…”