Estimation of life-cycle costs of buildings: regression vs artificial neural network

Abstract

Purpose-The purpose of this study is to compare the performance of regression and artificial-neuralnetworks (ANNs) methods to estimate the running-cost of building-projects towards improved accuracy. Design/methodology/approach-A data-set of 20 building-projects is used to test the performance of these two (ANNs/regression) models in estimating running cost. The concept of cost-significant-items is identified as important in assisting estimation. In addition, a stepwise technique is used to eliminate insignificant factors in regression-modelling. A connection-weight method is applied to determine the importance of cost factors in the performance of ANNs. Findings-The results illustrate that the value of the coefficient of determination = 99.75% for ANNs model(s), with a value of 98.1% utilising multiple-regression-model(s); secondly, the mean percentage error for ANNs at a testing stage is 0.179, which is less than that of the mean percentage error gained through multipleregression-modelling of 1.28; and thirdly, the average accuracy is 99% for ANNs model(s) and 97% for multiple-regression-model(s). On the basis of these results, it is concluded that an ANNs model is superior to a multiple-regression-model when predicting running-cost of building projects. Research limitations/implications-A means for continuous improvement for the performance of the models accuracy has been established; this may be further enhanced by future extended sample. Originality/value-This work extends the knowledge base of life-cycle estimation where ANNs method has been found to reduce preparation time consumed and increasing accuracy improvement of the cost estimation.

Residential Real Estate Valuation Framework Based on Life Cycle Cost by Building Information Modeling

“…Besides depicting LCC's benefits in valuation and investment decision-making, a practical framework for its implementation is required (Muñoz and Arayici 2015). Virtual reality, web, object-oriented technologies, CAD methods, multiple regression models, and artificial neural networks have been suggested in previous studies (Alqahtani and Whyte 2016). Standards like UniFormat and MasterFormat and coding systems like TBT and GB50500 have been utilized for cost breakdown structure (Ma et al 2013).…”