Genetic algorithm (GA) is a model of machine learning. The algorithm can be used to find sub‐optimum, if not optimum, solution(s) to a particular problem. It explores the solution space in an intelligent manner to evolve better solutions. The algorithm does not need any specific programming efforts but requires encoding the solution as strings of parameters. The field of application of genetic algorithms has increased dramatically in the last few years. A large variety of possible GA application tools now exist for non‐computer specialists. Complicated problems in a specific optimization domain can be tackled effectively with a very modest knowledge of the theory behind genetic algorithms. This paper reviews the technique briefly and applies it to solve some of the optimization problems addressed in construction management literature. The lessons learned from the application of GA to these problems are discussed. The result of this review is an indication of how the GA can contribute in solving construction‐related optimization problems. A summary of general guidelines to develop solutions using this optimization technique concludes the paper.

Genetic algorithm (GA) is a model of machine learning. The algorithm can be used to find sub‐optimum, if not optimum, solution(s) to a particular problem. It explores the solution space in an intelligent manner to evolve better solutions. The algorithm does not need any specific programming efforts but requires encoding the solution as strings of parameters. The field of application of genetic algorithms has increased dramatically in the last few years. A large variety of possible GA application tools now exist for non‐computer specialists. Complicated problems in a specific optimization domain can be tackled effectively with a very modest knowledge of the theory behind genetic algorithms. This paper reviews the technique briefly and applies it to solve some of the optimization problems addressed in construction management literature. The lessons learned from the application of GA to these problems are discussed. The result of this review is an indication of how the GA can contribute in solving construction‐related optimization problems. A summary of general guidelines to develop solutions using this optimization technique concludes the paper.

This paper describes a neural network model that can provide assistance in predicting the additional increase in project cost, due to political risk source variables affecting a construction project. The risk factors that affect a construction project are classified as “political source variables” and “project consequence variables.” These source variables are identified and represented in a neural network model. The paper explains how the developed political risk control model can be incorporated directly into a project cost estimation process. The paper concludes with a discussion of the capabilities and limitations of the proposed political risk estimation method, and how it will assist project managers in computing a realistic cost estimate for typical international construction projects under different political conditions.

Within the field of project management, research in the subject of conflict analysis and resolution has received considerable attention. This paper presents the application of cognitive analysis, based on the workings of “human judgment theorists,” to the resolution of representative conflict situations. The employed conflict-resolution approach presents cognitive differences between parties as a primary source of conflict. However, it also presents feedback that provides analysis of each individual's judgment and comparisons with his or her counterpart's judgment. This feedback, termed “cognitive feedback,” is used as a way to give insight to people in conflict, providing them an opportunity to resolve their conflicts acceptably. The objective of this paper is to establish a systematic methodology for analyzing and resolving conflict. An actual case study of conflict resolution between union and management personnel at a petrochemical plant in Kuwait is used to illustrate the methodology. Both self-understanding and the understanding of one's counterpart were found to be generally poor before receiving cognitive feedback. The use of cognitive feedback for both groups proved feasible and helped reduce conflict.

Construction projects are susceptible to cost and time overruns. Variations from planned schedule and cost estimates can result in huge losses for owners and contractors. In extreme cases, the viability of the project itself is jeopardised as a result of variations from baseline plans. Hence new methods and techniques which assist project managers in forecasting the expected variance in schedule and cost should be developed. This paper proposes a judgment-based forecasting approach which will identify schedule variances from a baseline plan for typical construction projects. The proposed forecasting approach adopts multiple regression techniques and further utilises neural networks to capture the decision-making procedure of project experts involved in schedule monitoring and prediction. The models developed were applied to a multistorey building project under construction and were found feasible for use in similar construction projects. The advantages and limitations of these two modelling process for prediction of schedule variance are discussed. The developed models were integrated with existing project management computer systems for the convenient and realistic generation of revised schedules at appropriate junctures during the progress of the project.