JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT, cilt.142, 2016 (SCI İndekslerine Giren Dergi)
This paper investigates the adequacy of some nontraditional approaches to produce realistic forecasts of the final costs of building projects and compare them with forecasts produced by three traditional methods, the unit area costs (UAC), client detailed costs (UPA), and contract sums (CS). As a case study, data of the actual final costs and forecasts produced using the three traditional methods for 420 finished public building projects carried out in Turkey were collected. Based on 75% of the collected data (i.e.,316 projects), three cost models based on UAC, UPA, and CS were established. The remaining 25% of the data (104 projects) were used as control data for testing the accuracies of forecasts produced by the different approaches. Cost forecasts using five nontraditional approaches, namely multilayer perceptron (MLP), radial basis function (RBF), grid partitioning algorithm (GPA), reference class forecasting (RCF), and regression analysis (RA) were then produced and compared with the actual final costs of projects of the control data. The forecasts were compared using four standard error measures: root-mean-square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and overall index of model performance (OI). Results of the analysis have shown that although the efficacy of each method to produce forecasts closer to the actual final costs varied depending on the model used, in general however, RCF and RA seem to produce more accurate and realistic forecasts than the other methods. As such the work described in the paper represents valuable contributions to knowledge and practice, firstly because RCF has not been used or tested before for cost forecasting of building projects. Secondly such comparison among the various methods and approaches used has not been found in published literature. Finally the paper provides guidance as to what approach to use at what stage of the project as well as how realistic the expected forecasts are.