Affiliation:
1. Dayananda Sagar University
Abstract
Abstract
Petroleum products fuel the economic engine of a country. It is vital that accurate demand forecasting is done for these products. Various forecasting methods from simple methods like moving average to complex fuzzy logic have been used to forecast the demand for Petroleum products with varying degree of accuracy. This study compares the forecasting accuracy of two machine learning forecasting models namely Seasonal Auto Regressive Integrated Moving Average (SARIMA) and Neural Network to forecast the consumption of Gasoline (MS) and Diesel (HSD) in India and conclude which model is able to better predict the demand. To compare the forecast accuracy of models, Mean Absolute Percentage Error (MAPE) is used. The model with the lowest Mean Absolute Percentage Error (MAPE) is considered as the better forecasting model. The study concludes SARIMA and Neural Network are able to predict the consumption of Gasoline (MS) with almost equal accuracy while SARIMA is able to predict the consumption of Diesel (HSD) significantly better then Neural Network.
Publisher
Research Square Platform LLC
Reference11 articles.
1. Forecasting of demand using ARIMA model;Fattah J;International Journal of Engineering Business Management,2018
2. Forecasting the consumption of gasoline in transport sector in Pakistan based on ARIMA model;Waheed Bhutto A;Environmental Progress & Sustainable Energy,2017
3. Nochai, R., & Nochai, T. (2006, June). ARIMA model for forecasting oil palm price. In Proceedings of the 2nd IMT-GT Regional Conference on Mathematics, Statistics and applications (pp. 13–15).
4. Forecasting of energy production and consumption in Asturias (northern Spain);Chavez SG;Energy,1999
5. Forecasting the differences between various commercial oil prices in the Persian Gulf region by neural network;Movagharnejad K;Energy,2011