Efficacy of using univariate modelling techniques in tender price index forecasting

Research output: Conference Papers (RGC: 31A, 31B, 32, 33)32_Refereed conference paper (no ISBN/ISSN)peer-review

View graph of relations

Detail(s)

Original languageEnglish
Publication statusPublished - 21 May 2017

Abstract

The construction industry is characterised with poor performance of project. Information gleaned from literature shows that uncertainty in cost is one of the significant causes of poor performance of construction projects. To address this problem, the present study developed two univariate models for tender price index forecasting. The Box-Jenkins and neural network models are the techniques adopted. The results show that the neural network model outperforms the Box-Jenkins model, in terms of accuracy and reliability. In addition, the neural network model provide a reliable forecast of tender price index over a period of 12 quarters ahead. The limitations of using the univariate models are elaborated. The developed neural network model can be used by stakeholders as a tool for predicting the movements in tender price index. In addition, the univariate models developed in the present study are particularly useful in developing countries, where limited data reduces the possibility of applying multivariate models.

Research Area(s)

  • Construction management, Construction economics