International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 09 Issue: 07 | July 2022
p-ISSN: 2395-0072
www.irjet.net
Cost Forecasting of Construction Materials: In India Cyril Thomas1, Jenson Jose2, Deepak Tom Babu3 1M.
Tech student, Dept. of civil Engineering, St. Joseph’s college of Engineering and Technology, Palai , Kerala, India 2Assistant Professor, Dept. of civil Engineering, St. Joseph’s college of Engineering and Technology, Palai, Kerala, India 3Project Associate, Centre for Industrial consultancy, St. Joseph’s college of Engineering and Technology, Palai, Kerala, India ---------------------------------------------------------------------***--------------------------------------------------------------------2. RESEARCH METHODOLOGY Abstract – In India the demand of construction sector is increasing day by day. Within 20 years we can expect a growth of 30% in the construction sector in India. The major reason for it may be the increased population and demand for industrial spaces. Now in India the Construction Cost Index (CCI) are widely used to forecast the construction costs. This research aims to forecast the construction material prices directly using ARIMA modeling followed by an Expert survey. So, it will be very beneficial for construction stakeholders, project owners, Engineers etc.
Different approaches have been analyzed to determine the best fitting model for forecasting construction costs. ARIMA modeling was selected based on the advice from the experts. And an expert survey also conducted and finally the results are compared.
2.1 Auto Regressive Integrated Moving Average method ARIMA (Auto Regressive Integrated Moving Average) method is an integration of Auto Regression model and Moving Average model. ARIMA model is represented as ARIMA (p, d, q). p represents number of auto regressive terms. q is the number of moving average terms. d is the order of differentiation to make the non-stationary series stationary. For modeling the historical data regarding material prices for past 15 years has been utilized. For cement, it was found that ARIMA (1,1,1) is the best fitting model and forecasting has been done with this model. Best ARIMA model is identified using following table.
Key Words: ARIMA, Cement, Steel, Brick, M sand.
1.INTRODUCTION Cost management is an important aspect in construction project management. Recently the construction material prices are subjected to large type of fluctuations depending on different factors. If the construction stake holders, project owners, contractors and engineers get an estimate regarding the future building material prices, it may be very beneficial for them in preparing future budgets. The modeling is done using IBM SPSS Statistics.
Table 1: Criteria for best ARIMA model
1.1 ARIMA Modeling ARIMA (Auto Regressive Integrated Moving Average) method is an efficient time series analysis method especially used for forecasting univariate time series data. This method is an integration of Auto Regression model and Moving Average model. This modeling method has been selected based on the advice from the experts.
An expert survey has been conducted to determine the future prices of building materials and the underlying causes. The survey was conducted all over India among the manufacturers, suppliers, cost analysts, purchase managers, project managers etc. The sample size is determined based on Cochran’s formula.
|
Impact Factor value: 7.529
Remarks
R-squared
Should be close to 1
RMSE (Root Squared Error)
1.2 Expert Survey
© 2022, IRJET
Model fit statistic
Mean
Lowest value indicates good model fit
MAPE (Mean Absolute Percentage Error)
Lowest value indicates good model fit
Normalized BIC
Least is the best
Model significance Value) Ljung BOX
|
(P-
Greater than 0.05 to accept HO: residuals are white noise
ISO 9001:2008 Certified Journal
|
Page 167