A computer based cost prediction model for institutional building projects in Nigeria: an artificial neural network approach. Issue 4 (22nd August 2014)

• Record Type: Journal Article
• Authors: Bala, Kabir; Bustani, Shehu Ahmad; Waziri, Baba Shehu
• Editors: Haupt, TheoC.
• Is Part Of: Journal of engineering, design and technology. Volume 12:Issue 4(2014)
• Publication Date: 2014-08-22
• Subjects: Engineering -- Periodicals; Engineering design -- Periodicals; Industrial design -- Periodicals; Technology -- Periodicals; 620.005
• DOI: 10.1108/JEDT-06-2012-0026
• Languages: English
• ISSNs: 1726-0531

Abstract

Abstract : Purpose: This study focused on developing a computer-based cost prediction model for institutional building projects in Nigeria through the use of Artificial Neural Network (ANN) technique. The back propagation network learns by example and provides good prediction to novel cases. Design/methodology/approach: The input variables were derived from related works with modification and advices from professionals through a field survey. 260 completed project data were used for training and development of the ANN model. Back propagation algorithm using the gradient descent delta learning rule with a learning coefficient of 0.4 was employed. The input layer of the model comprised of nine variables; building height, compactness of building, construction duration, external wall area, gross floor area, number of floors, proportion of opening on external walls, location index and time index. Findings: Several multi layer perceptron networks were developed with varying architecture from which the network 9 – 7 – 5 – 1 was selected. The performance of the model over the validation sample revealed that the model has a MAPE of 5.4% and average error of prediction of -2.5% over the sample. The ANN model was considered to be effective for construction cost prediction. Research limitations/implications: The Model may not be suitable for other building types because of the uniqueness of such facility even though significant difference is not anticipated for buildings such as commercial and residential. The models were evaluated based on the prediction errors; other means of evaluation were not employed. Originality/value: The study thus provides a simple, yet effective means of predicting construction costs of institutional building projects in Nigeria using an Artificial Neural Network model.