Claim Missing Document
Check
Articles

Found 1 Documents
Search

Forecasting Indonesia's Gross Domestic Product Using Extreme Learning Machine and Double Exponential Smoothing Bria, Anggelina Yuniance; Miswanto; Biyanto, Frasto; Siregar, Baldric
Indonesian Journal of Contemporary Multidisciplinary Research Vol. 4 No. 1 (2025): January 2025
Publisher : PT FORMOSA CENDEKIA GLOBAL

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55927/modern.v4i1.13265

Abstract

Gross Domestic Product (GDP) is one of the main indicators used to measure the economic condition of a country. Stable economic growth is crucial for achieving societal well-being; however, there are various factors that influence GDP fluctuations. Internal factors, such as ineffective fiscal and monetary policies, as well as external factors like changes in global economic conditions and geopolitical instability, can lead to instability in GDP growth. To improve GDP stability, appropriate fiscal and monetary policies, infrastructure investments, productivity enhancement, and the promotion of industry and the creative economy are necessary. This study employs two forecasting methods, namely Extreme Learning Machine (ELM) and Double Exponential Smoothing (DES), to analyze and predict economic growth based on historical GDP data. The results show that both methods can be used effectively to predict GDP growth, with ELM demonstrating superior ability in producing more accurate forecasts. By applying the right methods, it is expected that stable GDP growth can be achieved, leading to improved societal well-being and advancing the nation's progress.