Neural network models for intelligent support of mark-up estimation

Cost estimation is an important decision-making process where many factors are interrelated in a complex manner, thus making it difficult to analyse and model using conventional mathematical methods. Artificial neural networks (ANNs) offer an alternative approach to modelling cost estimation. ANNs are simple mathematical models that self-organize information from training data. This paper explores the use of ANNs in cost estimation. Research issues investigated are twofold. First, this paper compares the performance of ANNs to a regression-based method which leads to a better understanding of the applicability of ANNs. Second, this paper identifies the effect of different configurations of neural networks on estimating accuracy. Experimental results demonstrate the many advantages and disadvantages of using neural networks in modelling cost estimation.