The Construction Industry Development Council (CIDC) of India has been calculating and publishing the Construction Cost Index (CCI), monthly, since 1998. Construction cost variations interrogate different kinds of projects such as roads, power plants, buildings, industrial structures, railways and bridges. The success rate of completion of construction project is diminished due to the lack of prediction knowledge in CCI. Predicting CCI in greater accuracy is quite difficult for contractor and academicians. The following factors are influenced higher in CCI such as population, unemployment rate, consumer price index (CPI), long term interest rate, domestic credit growth, Gross Domestic Product (GDP) and money supply (M4). CCI can be used to forecast the construction cost. The relevant resource data was collected across the nation between 2003 and 2018. As outcome-based, non-econometric tools such as smoothing techniques, artificial neural network (ANN) and support vector machines (SVMs) have produced a better outcome. Among these, smoothing techniques have given the notable low error and high accuracy. This accuracy has measured by Mean Absolute Percentage Error (MAPE), Mean Square Error (MSE) and Root Mean Square Error (RMSE). The major objective of this research is to help the cost estimator to avoid underestimation and overestimation.
It is well known that the civil engineering constructions are subjected to cost risk and time overruns. The uncertainties of the cost of construction many times result in disputes among stakeholders. The recent cost fluctuation in sand price in Tamil Nadu is a good example of time and cost overruns. There are too many models developed to predict the cost of construction by using different parameters and tools. The objectives of this research are to analyse the importance of research in this field, the countries focusing on this issue, level of implementation by the practicing engineers, the tools often or successfully used, the difficulties in predicting the cost and the accuracy of prediction and bringing out a useful conclusion to provide the direction for future research. In this research, a sample of 324 research papers out of more than 2000 papers listed in Scopus database between the years 1990 and 2015 were considered and analyzed on five factors. The five factors are 1) authors affiliation – academics, industry or both; 2) country; 3) tools used – ANN, regression, time-series models, etc.; 4) complexity involved or ease of use; 5) accuracy of results. The results show interesting information.