Enhancing GDP Growth Forecasting with LSTM, GRU, and Hybrid Model: Evidence from South Korea

This study examines the application of Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRU) along with traditional econometric models in forecasting South Korea’s GDP growth. A hybrid framework is also developed, integrating these models through a meta-learner to capitalize on their c...

Full description

Saved in:
Bibliographic Details
Main Author: Dong-Jin Pyo
Format: Article
Language:English
Published: SAGE Publishing 2025-08-01
Series:SAGE Open
Online Access:https://doi.org/10.1177/21582440251359828
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849735422024876032
author Dong-Jin Pyo
author_facet Dong-Jin Pyo
author_sort Dong-Jin Pyo
collection DOAJ
description This study examines the application of Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRU) along with traditional econometric models in forecasting South Korea’s GDP growth. A hybrid framework is also developed, integrating these models through a meta-learner to capitalize on their complementary strengths. LSTM, with its ability to model nonlinear relationships and capture long-term dependencies, demonstrates accuracy improvements, especially during periods of economic volatility, such as the COVID-19 pandemic. The hybrid model further enhances forecasting performance by dynamically combining the strengths of LSTM and GRU with traditional approaches. This study provides a robust methodological contribution by uniting machine learning and econometric techniques, demonstrating their combined potential for enhancing forecasting accuracy and effectively addressing the complexities of diverse economic conditions.
format Article
id doaj-art-e5497642081543bd851e277be4d82300
institution DOAJ
issn 2158-2440
language English
publishDate 2025-08-01
publisher SAGE Publishing
record_format Article
series SAGE Open
spelling doaj-art-e5497642081543bd851e277be4d823002025-08-20T03:07:34ZengSAGE PublishingSAGE Open2158-24402025-08-011510.1177/21582440251359828Enhancing GDP Growth Forecasting with LSTM, GRU, and Hybrid Model: Evidence from South KoreaDong-Jin Pyo0Changwon National University, Republic of KoreaThis study examines the application of Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRU) along with traditional econometric models in forecasting South Korea’s GDP growth. A hybrid framework is also developed, integrating these models through a meta-learner to capitalize on their complementary strengths. LSTM, with its ability to model nonlinear relationships and capture long-term dependencies, demonstrates accuracy improvements, especially during periods of economic volatility, such as the COVID-19 pandemic. The hybrid model further enhances forecasting performance by dynamically combining the strengths of LSTM and GRU with traditional approaches. This study provides a robust methodological contribution by uniting machine learning and econometric techniques, demonstrating their combined potential for enhancing forecasting accuracy and effectively addressing the complexities of diverse economic conditions.https://doi.org/10.1177/21582440251359828
spellingShingle Dong-Jin Pyo
Enhancing GDP Growth Forecasting with LSTM, GRU, and Hybrid Model: Evidence from South Korea
SAGE Open
title Enhancing GDP Growth Forecasting with LSTM, GRU, and Hybrid Model: Evidence from South Korea
title_full Enhancing GDP Growth Forecasting with LSTM, GRU, and Hybrid Model: Evidence from South Korea
title_fullStr Enhancing GDP Growth Forecasting with LSTM, GRU, and Hybrid Model: Evidence from South Korea
title_full_unstemmed Enhancing GDP Growth Forecasting with LSTM, GRU, and Hybrid Model: Evidence from South Korea
title_short Enhancing GDP Growth Forecasting with LSTM, GRU, and Hybrid Model: Evidence from South Korea
title_sort enhancing gdp growth forecasting with lstm gru and hybrid model evidence from south korea
url https://doi.org/10.1177/21582440251359828
work_keys_str_mv AT dongjinpyo enhancinggdpgrowthforecastingwithlstmgruandhybridmodelevidencefromsouthkorea