Publications

Detailed Information

Nonlinear ARMA-GARCH Forecasting for S&P500 Index based on Recurrent Neural Networks : 순환신경망 기반 비선형 ARMA-GARCH 모형을 이용한 S&P500 지수 예측

DC Field Value Language
dc.contributor.advisor이상열-
dc.contributor.author정용진-
dc.date.accessioned2019-10-18T18:22:36Z-
dc.date.available2020-03-02T02:36:16Z-
dc.date.issued2019-08-
dc.identifier.other000000156578-
dc.identifier.urihttps://hdl.handle.net/10371/161660-
dc.identifier.urihttp://dcollection.snu.ac.kr/common/orgView/000000156578ko_KR
dc.description학위논문(석사)--서울대학교 대학원 :자연과학대학 통계학과,2019. 8. 이상열.-
dc.description.abstractA nonlinear ARMA-GARCH model is proposed for forecasting daily stock market returns. The only difference from the linear ARMA-GARCH is the conditional mean component. Two parameters are added and the hyperbolic tangent function is utilized to give a nonlinearity. The nonlinear ARMA-GARCH is solved by the recurrent neural network concept. In order to show the practical applicability of the proposed nonlinear ARMA-GARCH model, daily algorithmic trading is carried out with historical S&P500 daily closing index from 1950 to 2018. It is shown that the proposed nonlinear ARMA-GARCH model outperforms the linear ARMA-GARCH model in terms of financial and statistical measures.-
dc.description.abstract일별 주가 예측을 위한 순환신경망 기반 비선형 ARMA-GARCH 모형이 제안되었다. 기본적인 선형 ARMA-GARCH 모형에 두 개의 모수가 더해지고 쌍곡탄젠트함수를 이용하여 비선형성이 추가된 모형이다. 제안된 비선형 ARMA-GARCH 모형의 해는 순환신경망 개념을 이용하여 얻었다. 제안된 모형의 현실적 적용 가능성을 보이기 위하여 1950년부터 2018년까지 S&P500 지수의 일별 종가를 이용하여 알고리즘 기반 거래를 수행하였다. 금융 및 통계적 측도로 비교하였을 때 제안된 비선형 ARMA-GARCH 모형이 기존의 선형 ARMA-GARCH 모형보다 뛰어남을 보였다.-
dc.description.tableofcontentsAbstract i
List of Figures iii
List of Tables iv
Chapter 1 Introduction 1
Chapter 2 Data Description 3
Chapter 3 Model Description 6
3.1 Nonlinear ARMA-GARCH Model 7
3.2 Recurrent Neural Networks Structure 8
3.3 Model Selection 10
3.4 Trading Strategies 12
Chapter 4 Results 13
Chapter 5 Concluding Remarks 17
Bibliography 18
국문초록 22
-
dc.language.isoeng-
dc.publisher서울대학교 대학원-
dc.subjectNonlinear ARMA-GARCH-
dc.subjectrecurrent neural networks-
dc.subjectfinancial time series forecasting-
dc.subjectS&P500-
dc.subject.ddc519.5-
dc.titleNonlinear ARMA-GARCH Forecasting for S&P500 Index based on Recurrent Neural Networks-
dc.title.alternative순환신경망 기반 비선형 ARMA-GARCH 모형을 이용한 S&P500 지수 예측-
dc.typeThesis-
dc.typeDissertation-
dc.contributor.AlternativeAuthorYongjin Jeong-
dc.contributor.department자연과학대학 통계학과-
dc.description.degreeMaster-
dc.date.awarded2019-08-
dc.contributor.major통계학-
dc.identifier.uciI804:11032-000000156578-
dc.identifier.holdings000000000040▲000000000041▲000000156578▲-
Appears in Collections:
Files in This Item:

Altmetrics

Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Share