Volatility forecast of CIDC Construction Cost Index using smoothing techniques and machine learning

Abstract

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.

İnşaat Maliyet Endeksi Tahmininde Holt-Winters Üstel Düzeltme Parametrelerinin PSO ve İleri Walk-Forward Cross-Validation ile Optimizasyonu

“…Notably, the predictability of both models surpasses that of forecasts produced by ENR subject matter experts. This finding positions the developed Holt ES model as a tool to make more precise estimates for contractors and owners, ultimately contributing to the reduction of construction costs through well-timed project execution (Velumani & Nampoothiri, 2021).…”

“…Various forecasting models and techniques have been used to predict the CCI, encompassing linear forecasting models, ES methodologies such as Holt ES and Holt-Winters ES, multivariate time series models, and smoothing techniques (Choi et al, 2021;2010;Velumani & Nampoothiri, 2021). These models draw insights from historical data and the intrinsic attributes of the CCI to systematic forecasts (Velumani & Nampoothiri, 2021).…”

“…Another contribution by Velumani and Nampoothiri (2021) revolves around the development of two ES models aimed at forecasting the volatility of the Construction Industry Development Council CCI. In this endeavour, Holt ES and Holt-Winters ES methodologies are applied.…”

“…It also guides resource allocation, project planning, and financial reporting while keeping track of cost changes influenced by economic factors to manage risks effectively (Liu et al, 2021). Within the construction sector, the CCI serves as a significant metric, assessing cost trends and facilitating estimation and budgeting endeavours (Velumani & Nampoothiri, 2021). Ensuring accurate forecasts of the CCI is useful for cost estimators and contractors, enabling them to create precise bids and steer clear of under or overestimations (Ashuri & Lu, 2010).…”