Mohamedein, S. M. and Nassar, A. H. (2026) Calculating cost contingency for residential construction projects in Egypt using a machine learning algorithm. International Journal of Construction Management, 26(9), pp. 1761-1776. ISSN 1562-3599
Abstract
Cost contingency (CC) is a critical factor in residential construction projects, as it has several negative consequences for project owners if underestimated. If the cost contingency (CC) is too high, it might cause the construction project to be uneconomical; if it is too low, it may result in unacceptable performance consequences. This research presents an Artificial Neural Network (ANN) machine learning model that allows owners to accurately predict the project's cost contingency (CC) for residential construction projects in Egypt. The main factors have been identified and defined as data input variables for the model. Furthermore, the model layers are identified, with the output being the cost contingency as a percentage of the project. Two scenarios are mentioned to develop the most accurate prediction for the contingency using 20 sets of actual residential project data. Based on the best model prediction, testing and validation were completed. The model was tested and validated with an acceptable Symmetric Mean Absolute Percentage Error (sMAPE) of 19.5% for residential projects' cost contingency (CC).
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | artificial neural networks; cost contingency; symmetric mean absolute percentage error |
| Index terms: | critical factor, construction project, residential project, residential construction, Egypt, machine learning, artificial neural network, testing, validation, owner |
| Subjects: | professional development, professional practice, production management, risk assessment, economic development, modelling and simulation, artificial intelligence, sociology, construction integration, Geography |
| Topics: | Risk Management, Engineering Principles, Business Strategy, Stakeholder Management, Urban Studies, Project Management, Digital Applications, Research Practice, Geographical Context, Information Management |
| Descriptive scope: | 2 PC |
N.B. Descriptive scope is a count of how many of the five facets of empirical research are indicated by the words used in title, abstract and keywords. It is not intended as a judgement on the research; merely a count of the kind of word we would expect to indicate Phenomenon, Concepts, Theoretical framing, Empirical techniques, Analytical techniques. If all five are present, then a code of “5 PCTEA” will indicate this. If you feel the coding for this record is questionable, we welcome discussion around the terms we matched or the way we categorized them. The facet you would expect may not be coded, or a facet may be coded inappropriately. This can also bear on a larger question, of which facets should be treated as defining in construction management research. Please get in touch, and we will look at it. More details here