Dian Kurniasari, Sulistian Oskavina, W. Wamiliana, W. Warsono
{"title":"Forecasting The Value of Indonesian Oil-Non-Oil and Gas Imported Using The Gated Recurrent Unit (GRU)","authors":"Dian Kurniasari, Sulistian Oskavina, W. Wamiliana, W. Warsono","doi":"10.24014/ijaidm.v6i1.20651","DOIUrl":null,"url":null,"abstract":"In Indonesia, various factors play a role in economic development. Oil-non-oil and gas imports are one of the main factors. However, the value of oil-non-oil and gas imports in Indonesia fluctuates monthly. Therefore, an appropriate method is required to monitor changes in the value of oil-non-oil and gas imports in Indonesia so that the government can make the right choices. This study uses the GRU method to estimate the amount of oil-non-oil and gas imports in Indonesia. The best model for forecasting over the next two years has an optimum structure of 32 GRU units, 16 batch sizes, and 100 epochs, with a dropout of 0.2 and uses 80% training data and 20% test data. The MAPE value obtained is 0.999955%, with an accuracy of 99.000044%. Forecast results suggest an improvement from June 2022 to July 2024.","PeriodicalId":385582,"journal":{"name":"Indonesian Journal of Artificial Intelligence and Data Mining","volume":"190 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Indonesian Journal of Artificial Intelligence and Data Mining","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.24014/ijaidm.v6i1.20651","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In Indonesia, various factors play a role in economic development. Oil-non-oil and gas imports are one of the main factors. However, the value of oil-non-oil and gas imports in Indonesia fluctuates monthly. Therefore, an appropriate method is required to monitor changes in the value of oil-non-oil and gas imports in Indonesia so that the government can make the right choices. This study uses the GRU method to estimate the amount of oil-non-oil and gas imports in Indonesia. The best model for forecasting over the next two years has an optimum structure of 32 GRU units, 16 batch sizes, and 100 epochs, with a dropout of 0.2 and uses 80% training data and 20% test data. The MAPE value obtained is 0.999955%, with an accuracy of 99.000044%. Forecast results suggest an improvement from June 2022 to July 2024.