India's dependence on foreign oil will exceed 90% around 2025 - The forecasting results based on two hybridized NMGM-ARIMA and NMGM-BP models

Abstract

Few study has been conducted to forecast India's dependence on foreign oil, although India is the world's third-largest oil consumer and exporter, making it a key player in the oil market. This work is aimed to accurately forecast India's dependence on foreign oil. To develop better forecasting techniques, this study used linear Auto Regressive Integrated Moving Average (ARIMA), and nonlinear Back Propagation (BP) to correct nonlinear metabolic grey model (NMGM) forecasting residuals in three steps: (i) integrating the metabolic idea with a nonlinear grey model to develop NMGM, (ii) integrating the proposed NMGM with ARIMA to develop NMGM-ARIMA, and (iii) integrating the proposed NMGM with BP to develop NMGM-BP. To further improve forecasting accuracy, this work forecasted the India's dependence on foreign oil from two perspectives: (i) direct forecasting the change of ratio of imports oil to total oil consumption in India, (ii) indirect forecasting, i.e., the difference between the forecasted oil consumption and production was divided by the forecasted oil production. The proposed NMGM-ARIMA and NMGM-BP were used to fit the India's dependence on foreign oil for 1995–2017 and forecast the data for 2018–2030. The mean relative error of the proposed forecasting models was around 1.5%, which could produce a convincing forecasting results. Our forecasting results show that India's dependence on foreign oil will reach 90% around 2025, which poses serious challenge to Indian oil security and the global oil market.