Title Development of an Optimal Model for Forecasting Overseas Construction Orders
Authors Lee, Kwangwon ; Jo, Woonghyeon
DOI http://dx.doi.org/10.6106/KJCEM.2020.21.4.030
Page pp.30-37
ISSN 2005-6095
Keywords Overseas Construction Order; Time-series Analysis; VAR Model
Abstract The purpose of this study is to compare and contrast the amount of overseas construction orders of South Korea and China by using various time series models that measure the overseas construction orders. Based on the analysis we propose better specification (model selection) with much more predictive power and prove the universality of the model developed by applying our findings with respect to the prediction power of overseas construction orders from other countries viewpoints (verification of generalization). The input variables include Dubai crude oil and exchange rates by country from 1981 to 2019. The VAR model is proposed based on the prediction power test, with respect to MAPE, RMSE, and MAE between the estimates and actual measurements from 2016 to 2019. We also conclude the results of the prediction of overseas construction orders time series of China are again consistent with the actual numbers. These analyses suggest the possibility of developing a comprehensive model that predict the potential construction orders of other countries.