Machine Learning of Forecasting Long-Term Economic Crisis in Indonesia

被引:0
|
作者
Sa'adah, Siti [1 ]
Liong, The Houw [1 ]
Adiwijaya [1 ]
机构
[1] Telecom Inst Technol, Fac Informat, Graduated Sch, Hanoi, Vietnam
关键词
machine learning; long term economic crisis; population; oil import;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Oil (energy) is huge influence of economic Indonesia. Since many sectors from Industries until individual need it. In fact, Indonesia is a country with high density population. Because of that, the necessity of oil must be meet amount of inhabitant in Indonesia. If government failed to answer the demand of oil, then Indonesia will be face economic crisis for long-term. So that, the forecast of it still need to be concerned. Furthermore, data about population and oil import were used to forecast economic condition. Shape of it had been done by machine learning. The result shows that the growth of population has influence of oil needed. Because when the population increases exponentially then the necessity of energy (oil) consumption followed. It roots of economic crisis in long-term. It can be proved from the accuracy result in training around 98%, while 90% in testing. By mean of that, Indonesia should concern more about population aging on economic growth refer to availability of oil. In other perspective, machine either show that the model forecast still find error. Error was caused by the use of few data; beside the aspect of economic is complex and chaos area.
引用
收藏
页码:261 / 266
页数:6
相关论文
共 50 条
  • [1] Machine learning in long-term mortality forecasting
    Qiao, Yang
    Wang, Chou-Wen
    Zhu, Wenjun
    [J]. GENEVA PAPERS ON RISK AND INSURANCE-ISSUES AND PRACTICE, 2024, 49 (02): : 340 - 362
  • [2] An Investigation into the Efficacy of Machine Learning Models for Long-term Forecasting
    Issi, Fatih
    [J]. 12TH INTERNATIONAL CONFERENCE ON SMART GRID, ICSMARTGRID 2024, 2024, : 487 - 492
  • [3] Comparison of the long-term forecasting method of RSSI by machine learning
    Nagao, Tatsuya
    Hayashi, Takahiro
    Amano, Yoshiaki
    [J]. IEICE COMMUNICATIONS EXPRESS, 2020, 9 (11): : 553 - 558
  • [4] Forecasting benchmarks of long-term stock returns via machine learning
    Kyriakou, Ioannis
    Mousavi, Parastoo
    Nielsen, Jens Perch
    Scholz, Michael
    [J]. ANNALS OF OPERATIONS RESEARCH, 2021, 297 (1-2) : 221 - 240
  • [5] Long-term Traffic Forecasting in Optical Networks Using Machine Learning
    Walkowiak, Krzysztof
    Szostak, Daniel
    Wlodarczyk, Adam
    Kasprzak, Andrzej
    [J]. INTERNATIONAL JOURNAL OF ELECTRONICS AND TELECOMMUNICATIONS, 2023, 69 (04) : 751 - 762
  • [6] Forecasting benchmarks of long-term stock returns via machine learning
    Ioannis Kyriakou
    Parastoo Mousavi
    Jens Perch Nielsen
    Michael Scholz
    [J]. Annals of Operations Research, 2021, 297 : 221 - 240
  • [7] Forecasting long-term world annual natural gas production by machine learning
    Sen, Doruk
    Hamurcuoglu, K. Irem
    Ersoy, Melisa Z.
    Tunc, K. M. Murat
    Gunay, M. Erdem
    [J]. RESOURCES POLICY, 2023, 80
  • [8] Machine Learning based Electric Load Forecasting for Short and Long-term Period
    Vantuch, Tomas
    Gonzalez Vidal, Aurora
    Ramallo-Gonzalez, Alfonso P.
    Skarmeta, Antonio F.
    Misak, Stanislav
    [J]. 2018 IEEE 4TH WORLD FORUM ON INTERNET OF THINGS (WF-IOT), 2018, : 511 - 516
  • [9] Forecasting long-term world annual natural gas production by machine learning
    Sen, Doruk
    Hamurcuoglu, K. Irem
    Ersoy, Melisa Z.
    Tunc, K. M. Murat
    Gunay, M. Erdem
    [J]. RESOURCES POLICY, 2023, 80
  • [10] Long-Term Fundamentals of the 2008 Economic Crisis
    Mayer-Foulkes, David A.
    [J]. GLOBAL ECONOMY JOURNAL, 2009, 9 (04):