Forecasting High Speed Diesel Demand in India with Econometric and Machine Learning Methods
According to International Energy Agency (IEA), India is expected to surpass China by 2024 to become the second largest consumer of oil in the world followed by the United States. High-Speed Diesel (HSD) has the biggest share in the total petroleum products consumed in India accounting for around 3...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EconJournals
2024-01-01
|
| Series: | International Journal of Energy Economics and Policy |
| Subjects: | |
| Online Access: | https://econjournals.com/index.php/ijeep/article/view/15572 |
| _version_ | 1797353161081487360 |
|---|---|
| author | Aarti Mehta Sharma Saina Baby Varsha Raghu |
| author_facet | Aarti Mehta Sharma Saina Baby Varsha Raghu |
| author_sort | Aarti Mehta Sharma |
| collection | DOAJ |
| description |
According to International Energy Agency (IEA), India is expected to surpass China by 2024 to become the second largest consumer of oil in the world followed by the United States. High-Speed Diesel (HSD) has the biggest share in the total petroleum products consumed in India accounting for around 38% of the total consumption. Considering the volatile global oil market and an oil import dependency ratio of more than 80% during the last four years, the probability of supply disruptions is high in the Indian context. As any uncertainty about the supply of diesel can affect the smooth functioning of the economy and may create inflationary pressures. Accurate forecasting of HSD demand will be essential for appropriate supply management arrangements. Artificial Neural Networks (ANN) with Multi-Layer Perceptron (MLP) and extreme learning machines is used for forecasting diesel demand in this study. Demand forecasting has been carried out using monthly HSD demand data drawn from the “Indiastat” database for the period 1991-2022. Comparison of ANN with traditional forecasting methods of Autoregressive Integrated Moving Average(ARIMA)and Exponential Smoothing has also been undertaken in this study. This study identifies the deep learning technique of ANN with MLP as the best diesel demand forecasting technique.
|
| first_indexed | 2024-03-08T13:27:08Z |
| format | Article |
| id | doaj.art-09d3a6dc671a4ebc83412c1f1249ea29 |
| institution | Directory Open Access Journal |
| issn | 2146-4553 |
| language | English |
| last_indexed | 2024-03-08T13:27:08Z |
| publishDate | 2024-01-01 |
| publisher | EconJournals |
| record_format | Article |
| series | International Journal of Energy Economics and Policy |
| spelling | doaj.art-09d3a6dc671a4ebc83412c1f1249ea292024-01-17T14:42:33ZengEconJournalsInternational Journal of Energy Economics and Policy2146-45532024-01-0114110.32479/ijeep.15572Forecasting High Speed Diesel Demand in India with Econometric and Machine Learning MethodsAarti Mehta Sharma0Saina Baby1Varsha Raghu2Symbiosis Centre for Management Studies, Bengaluru, Symbiosis International (Deemed University), Pune, Maharashtra, IndiaSymbiosis Institute of Business Management Bengaluru, Symbiosis International (Deemed University), Pune, Maharashtra, India,Freelance Researcher, India. According to International Energy Agency (IEA), India is expected to surpass China by 2024 to become the second largest consumer of oil in the world followed by the United States. High-Speed Diesel (HSD) has the biggest share in the total petroleum products consumed in India accounting for around 38% of the total consumption. Considering the volatile global oil market and an oil import dependency ratio of more than 80% during the last four years, the probability of supply disruptions is high in the Indian context. As any uncertainty about the supply of diesel can affect the smooth functioning of the economy and may create inflationary pressures. Accurate forecasting of HSD demand will be essential for appropriate supply management arrangements. Artificial Neural Networks (ANN) with Multi-Layer Perceptron (MLP) and extreme learning machines is used for forecasting diesel demand in this study. Demand forecasting has been carried out using monthly HSD demand data drawn from the “Indiastat” database for the period 1991-2022. Comparison of ANN with traditional forecasting methods of Autoregressive Integrated Moving Average(ARIMA)and Exponential Smoothing has also been undertaken in this study. This study identifies the deep learning technique of ANN with MLP as the best diesel demand forecasting technique. https://econjournals.com/index.php/ijeep/article/view/15572High Speed Diesel, Forecasting, Time Series, ANN, Accuracy, ARIMA, Exponential Smoothing |
| spellingShingle | Aarti Mehta Sharma Saina Baby Varsha Raghu Forecasting High Speed Diesel Demand in India with Econometric and Machine Learning Methods International Journal of Energy Economics and Policy High Speed Diesel, Forecasting, Time Series, ANN, Accuracy, ARIMA, Exponential Smoothing |
| title | Forecasting High Speed Diesel Demand in India with Econometric and Machine Learning Methods |
| title_full | Forecasting High Speed Diesel Demand in India with Econometric and Machine Learning Methods |
| title_fullStr | Forecasting High Speed Diesel Demand in India with Econometric and Machine Learning Methods |
| title_full_unstemmed | Forecasting High Speed Diesel Demand in India with Econometric and Machine Learning Methods |
| title_short | Forecasting High Speed Diesel Demand in India with Econometric and Machine Learning Methods |
| title_sort | forecasting high speed diesel demand in india with econometric and machine learning methods |
| topic | High Speed Diesel, Forecasting, Time Series, ANN, Accuracy, ARIMA, Exponential Smoothing |
| url | https://econjournals.com/index.php/ijeep/article/view/15572 |
| work_keys_str_mv | AT aartimehtasharma forecastinghighspeeddieseldemandinindiawitheconometricandmachinelearningmethods AT sainababy forecastinghighspeeddieseldemandinindiawitheconometricandmachinelearningmethods AT varsharaghu forecastinghighspeeddieseldemandinindiawitheconometricandmachinelearningmethods |