JOURNAL ARTICLE

Financial time series forecasting using AdaBoost-GRU ensemble model

Nae Won KwakDong Hoon Lim

Year: 2021 Journal:   Journal of the Korean Data and Information Science Society Vol: 32 (2)Pages: 267-281   Publisher: The Korean Data and Information Science Society (KDISS)

Abstract

일반적으로 금융 시계열 (financial time series) 예측은 비선형성 (non-linearity)과 불규칙성(irregularity)으로 인해 매우 어려운 일이다. 본 논문에서는 금융 시계열 예측을 위해 AdaBoost 알고리즘과 GRU 모형을 결합한 하이브리드 앙상블 학습 방법 (hybrid ensemble learning approach)을 제안하고자 한다. 여기서 GRU 모형은 LSTM (long short term memory) 모형과 함께 시계열 예측에 널리 사용되는 RNN (recurrent neural network)의 변형 모형이다. 우리는 KOSPI 데이터와 원/달러 환율과 같은 금융 시계열 데이터를 가지고 제안된 모델을 평가하고자 한다. 성능실험 결과 제안된 AdaBoost-GRU 앙상블은 3가지 척도 즉, MAE, MSE 및 RMSE 척도에서 기존의 ARIMA 모형, LSTM 모형, GRU 모형, 그리고 Adaboost-LSTM 앙상블보다 좋은 성능을 보였다. 그리고 Adaboost-LSTM 모형과의 처리속도 면에서 제안된 AdaBoost-GRU 모형이 빠름을 알 수 있었다.

Keywords:
AdaBoost Artificial intelligence Series (stratigraphy) Computer science Autoregressive integrated moving average Pattern recognition (psychology) Recurrent neural network Machine learning Time series Artificial neural network Support vector machine

Metrics

6
Cited By
1.16
FWCI (Field Weighted Citation Impact)
0
Refs
0.82
Citation Normalized Percentile
Is in top 1%
Is in top 10%

Citation History

Topics

Advanced Decision-Making Techniques
Physical Sciences →  Computer Science →  Information Systems
Advanced Sensor and Control Systems
Physical Sciences →  Engineering →  Control and Systems Engineering
Wireless Sensor Networks and IoT
Physical Sciences →  Engineering →  Control and Systems Engineering

Related Documents

BOOK-CHAPTER

AdaBoost-LSTM Ensemble Learning for Financial Time Series Forecasting

Shaolong SunYunjie WeiShouyang Wang

Lecture notes in computer science Year: 2018 Pages: 590-597
JOURNAL ARTICLE

An Application of AdaBoost-GRU Ensemble Model to Economic Time Series Prediction

Ganiyu Adewale BusariNae Won KwakDong Hoon LimDong H Lim

Journal:   Indian Journal of Science and Technology Year: 2021 Vol: 14 (31)Pages: 2557-2566
BOOK-CHAPTER

Forecasting Cryptocurrency Time Series Using Adaboost-Based Ensemble Learning Techniques

Haritima ManchandaSwati Aggarwal

Lecture notes in electrical engineering Year: 2021 Pages: 207-219
JOURNAL ARTICLE

Adaboost-Based Long Short-Term Memory Ensemble Learning Approach for Financial Time Series Forecasting

Yungao WuJianwei Gao

Journal:   Current Science Year: 2018 Vol: 115 (1)Pages: 159-159
© 2026 ScienceGate Book Chapters — All rights reserved.