Oil Demand Forecasting in Malaysia in Transportation Sector using Artificial Neural Network (ANN)

Energy industry in Malaysia is one of critical sector that plays an important role in contributing the nation economic growth. The main energy source in Malaysia is from the petroleum and natural gas while the sector that consumed the most energy is transportation sector. Since both of these are the main energy source and consumer, a forecasting model is required to be developed to provide the oil demand forecast in transportation sector. This research analyses different forecasting models including time series regression technique, Auto Regressive Integrated Moving Average (ARIMA), double moving average method, double exponential smoothing method, triple exponential smoothing method and Artificial Neural Network (ANN) model (Univariate and Multivariate) to predict the future oil demand in transportation sector in Malaysia. In order to select the best forecasting model, the model validation is done using the error analysis technique such as Root Mean Square Error (RMSE), Mean Percentage Error (MPE), Mean Absolute Percentage Error (MAPE) and Correlation Coefficient (R2). Based on the model validation result, it is found that the Artificial Neural Network gives the least error in all of the error analysis techniques. Thus, Artificial Neural Network model is used to forecast the oil demand in transportation sector in Malaysia. The oil demand forecasted by the model in transportation sector in Malaysia for the year 2020, 2025 and 2030 are 559.44, 581.779 and 609.941 kg of oil equivalent respectivel