주가의 기술적 지표를 이용한 단방향·양방향 LSTM 모델의 주가 예측 분석

본 논문은 LSTM(Long Short-Term Memory) 모델을 활용한 주가 예측에서 추가적인 입력 변수인 기술적 지표 활용 여부가 모델 성능에 미치는 영향을 분석하고, 단방향 및 양방향 모델 간의 성능 차이를 비교하였다. 입력값으로는 시가, 종가, 저가, 고가, 거래량을 사용하였으며, 상대강도지수와 변동성을 추가적인 입력 변수로 선택하였다. 기술적 지표를 포함하지 않은 모델과 포함한 모델을 각각 단방향 및 양방향 LSTM 모델의 성능을 비교 분석하였으며, 성능 평가는 평균 제곱근 오차를 기준으로 평가하였다. 실험 결과 기술적...

Full description

Saved in:
Bibliographic Details
Published inInteonet jeongbo hakoe nonmunji = Journal of Korean Society for Internet Information Vol. 26; no. 3; pp. 111 - 119
Main Authors 류종우, Jong-woo Ryu, 백건희, Geon-hee Baek, 남춘성, Choon-sung Nam
Format Journal Article
LanguageKorean
Published 한국인터넷정보학회 30.06.2025
Subjects
Online AccessGet full text
ISSN1598-0170
2287-1136
DOI10.7472/jksii.2025.26.3.111

Cover

Abstract 본 논문은 LSTM(Long Short-Term Memory) 모델을 활용한 주가 예측에서 추가적인 입력 변수인 기술적 지표 활용 여부가 모델 성능에 미치는 영향을 분석하고, 단방향 및 양방향 모델 간의 성능 차이를 비교하였다. 입력값으로는 시가, 종가, 저가, 고가, 거래량을 사용하였으며, 상대강도지수와 변동성을 추가적인 입력 변수로 선택하였다. 기술적 지표를 포함하지 않은 모델과 포함한 모델을 각각 단방향 및 양방향 LSTM 모델의 성능을 비교 분석하였으며, 성능 평가는 평균 제곱근 오차를 기준으로 평가하였다. 실험 결과 기술적 지표를 추가한 모델이 예측 성능에서 더 낮은 평균 제곱근 오차를 보이며 정확도가 높은 것을 확인하였다. 또한, 양방향 LSTM 모델이 단방향 LSTM 모델에 비해 전반적으로 더 우수한 성능을 보였다. This paper analyzes the effect of whether or not to utilize additional features on th model performance in stock price prediction using the LSTM(Long Short-Term Memory) model and compares the performance difference between the unidirectional and bidirectional models. Opening price, closing price, low price, high price, and trading volume were used as input values, and the RSI(Relative Strength Index) and volatility were selected as additional features. The performance of the unidirectional and bidirectional LSTM models that did not include features and the unidirectional and bidirectional LSTM models were compared and analyzed, respectively, and the performance evaluation was evaluated based on the RMSE(Root Mean Square Error). As a result of the experiment, it was confirmed that the model to which the RSI and volatility were added showed a lower RMSE in the prediction performance and improved accuracy. In addition, the bidirectional LSTM model showed better overall performance than the unidirectional LSTM model.
AbstractList 본 논문은 LSTM(Long Short-Term Memory) 모델을 활용한 주가 예측에서 추가적인 입력 변수인 기술적 지표 활용 여부가 모델 성능에 미치는 영향을 분석하고, 단방향 및 양방향 모델 간의 성능 차이를 비교하였다. 입력값으로는 시가, 종가, 저가, 고가, 거래량을 사용하였으며, 상대강도지수와 변동성을 추가적인 입력 변수로 선택하였다. 기술적 지표를 포함하지 않은 모델과 포함한 모델을 각각 단방향 및 양방향 LSTM 모델의 성능을 비교 분석하였으며, 성능 평가는 평균 제곱근 오차를 기준으로 평가하였다. 실험 결과 기술적 지표를 추가한 모델이 예측 성능에서 더 낮은 평균 제곱근 오차를 보이며 정확도가 높은 것을 확인하였다. 또한, 양방향 LSTM 모델이 단방향 LSTM 모델에 비해 전반적으로 더 우수한 성능을 보였다. This paper analyzes the effect of whether or not to utilize additional features on th model performance in stock price prediction using the LSTM(Long Short-Term Memory) model and compares the performance difference between the unidirectional and bidirectional models. Opening price, closing price, low price, high price, and trading volume were used as input values, and the RSI(Relative Strength Index) and volatility were selected as additional features. The performance of the unidirectional and bidirectional LSTM models that did not include features and the unidirectional and bidirectional LSTM models were compared and analyzed, respectively, and the performance evaluation was evaluated based on the RMSE(Root Mean Square Error). As a result of the experiment, it was confirmed that the model to which the RSI and volatility were added showed a lower RMSE in the prediction performance and improved accuracy. In addition, the bidirectional LSTM model showed better overall performance than the unidirectional LSTM model.
본 논문은 LSTM(Long Short-Term Memory) 모델을 활용한 주가 예측에서 추가적인 입력 변수인 기술적 지표 활용 여부가 모델 성능에 미치는 영향을 분석하고, 단방향 및 양방향 모델 간의 성능 차이를 비교하였다. 입력값으로는 시가, 종가, 저가, 고가, 거래량을 사용하였으며, 상대강도지수와 변동성을 추가적인 입력 변수로 선택하였다. 기술적 지표를 포함하지 않은 모델과 포함한 모델을 각각 단방향 및 양방향 LSTM 모델의 성능을 비교 분석하였으며, 성능 평가는 평균 제곱근 오차를 기준으로 평가하였다. 실험 결과 기술적 지표를 추가한 모델이 예측 성능에서 더 낮은 평균 제곱근 오차를 보이며 정확도가 높은 것을 확인하였다. 또한, 양방향 LSTM 모델이 단방향 LSTM 모델에 비해 전반적으로 더 우수한 성능을 보였다. This paper analyzes the effect of whether or not to utilize additional features on th model performance in stock price prediction using the LSTM(Long Short-Term Memory) model and compares the performance difference between the unidirectional and bidirectional models. Opening price, closing price, low price, high price, and trading volume were used as input values, and the RSI(Relative Strength Index) and volatility were selected as additional features. The performance of the unidirectional and bidirectional LSTM models that did not include features and the unidirectional and bidirectional LSTM models were compared and analyzed, respectively, and the performance evaluation was evaluated based on the RMSE(Root Mean Square Error). As a result of the experiment, it was confirmed that the model to which the RSI and volatility were added showed a lower RMSE in the prediction performance and improved accuracy. In addition, the bidirectional LSTM model showed better overall performance than the unidirectional LSTM model. KCI Citation Count: 0
This paper analyzes the effect of whether or not to utilize additional features on th model performance in stock price prediction using the LSTM(Long Short-Term Memory) model and compares the performance difference between the unidirectional and bidirectional models. Opening price, closing price, low price, high price, and trading volume were used as input values, and the RSI(Relative Strength Index) and volatility were selected as additional features. The performance of the unidirectional and bidirectional LSTM models that did not include features and the unidirectional and bidirectional LSTM models were compared and analyzed, respectively, and the performance evaluation was evaluated based on the RMSE(Root Mean Square Error). As a result of the experiment, it was confirmed that the model to which the RSI and volatility were added showed a lower RMSE in the prediction performance and improved accuracy. In addition, the bidirectional LSTM model showed better overall performance than the unidirectional LSTM model. 본 논문은 LSTM(Long Short-Term Memory) 모델을 활용한 주가 예측에서 추가적인 입력 변수인 기술적 지표 활용 여부가 모델 성능에 미치는 영향을 분석하고, 단방향 및 양방향 모델 간의 성능 차이를 비교하였다. 입력값으로는 시가, 종가, 저가, 고가, 거래량을 사용하였으며, 상대강도지수와 변동성을 추가적인 입력 변수로 선택하였다. 기술적 지표를 포함하지 않은 모델과 포함한 모델을 각각 단방향 및 양방향 LSTM 모델의 성능을 비교 분석하였으며, 성능 평가는 평균 제곱근 오차를 기준으로 평가하였다. 실험 결과 기술적 지표를 추가한 모델이 예측 성능에서 더 낮은 평균 제곱근 오차를 보이며 정확도가 높은 것을 확인하였다. 또한, 양방향 LSTM 모델이 단방향 LSTM 모델에 비해 전반적으로 더 우수한 성능을 보였다.
Author 백건희
남춘성
류종우
Choon-sung Nam
Jong-woo Ryu
Geon-hee Baek
Author_xml – sequence: 1
  fullname: 류종우
– sequence: 2
  fullname: Jong-woo Ryu
– sequence: 3
  fullname: 백건희
– sequence: 4
  fullname: Geon-hee Baek
– sequence: 5
  fullname: 남춘성
– sequence: 6
  fullname: Choon-sung Nam
BackLink https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART003222238$$DAccess content in National Research Foundation of Korea (NRF)
BookMark eNo9kD1Lw1AYhS-iYNX-gi5ZXITE9743yc0di_hRrRQ0-zWpicTUVhoXtwodCuLgYCliQZHix9RBtEMnf05z-x9srTidw-HhGc4Sma_WqgEhOQoGNzmun8ZJFBkIaBloG8yglM6RDKLDdUqZPU8y1BKODpTDIskmSeSDxRjnTECGHKnn4ajfUN2ONhr0VetRPV5p6qUxvn1Ie0NNdT_U_dv47kFLr1_T_tu43fv-Uu3bWdWKh-6-lr6_pjeDqWHm0lSnpQZPWvrZVM3uClkIvUoSZP9ymbhbm-7Gjl4sbRc28kU9diyh-6YXhgIwpLbDOIXAclBYzDQZBe4LZtrAHUQfKAUAOwgDc7L6vAwUvTIGbJmszbTVeijjciRrXvSbJzUZ12X-wC3IiYohUjGBV2dwHCUXkaweJxW5m98rTT9EEEzYYCFjEy73zyXyvB6defVLaVIHHSbYD9cSibA
ContentType Journal Article
DBID HZB
Q5X
JDI
ACYCR
DEWEY 004
DOI 10.7472/jksii.2025.26.3.111
DatabaseName Korean Studies Information Service System (KISS)
Korean Studies Information Service System (KISS) B-Type
KoreaScience
Korean Citation Index
DatabaseTitleList


DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
DocumentTitleAlternate 주가의 기술적 지표를 이용한 단방향·양방향 LSTM 모델의 주가 예측 분석
Price Prediction Analysis Using Unidirectional and Bidirectional LSTM Models Based on Technical Indicators
EISSN 2287-1136
EndPage 119
ExternalDocumentID oai_kci_go_kr_ARTI_10732219
JAKO202520939605233
4182839
GroupedDBID .4S
AEMOZ
AHQJS
AKVCP
ALMA_UNASSIGNED_HOLDINGS
ARCSS
EBA
EBE
EBR
EBU
EDO
EPL
HZB
Q5X
TH9
TUS
JDI
ACYCR
ID FETCH-LOGICAL-k859-b4aff902f1683710e582953443107b934607822b0110006efe4b93b7c012ac2e3
ISSN 1598-0170
IngestDate Sun Jul 06 03:13:49 EDT 2025
Wed Sep 03 02:46:50 EDT 2025
Tue Aug 05 02:10:20 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed false
IsScholarly true
Issue 3
Language Korean
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-k859-b4aff902f1683710e582953443107b934607822b0110006efe4b93b7c012ac2e3
Notes Korean Society for Internet Information
KISTI1.1003/JNL.JAKO202520939605233
OpenAccessLink http://click.ndsl.kr/servlet/LinkingDetailView?cn=JAKO202520939605233&dbt=JAKO&org_code=O481&site_code=SS1481&service_code=01
PageCount 9
ParticipantIDs nrf_kci_oai_kci_go_kr_ARTI_10732219
kisti_ndsl_JAKO202520939605233
kiss_primary_4182839
PublicationCentury 2000
PublicationDate 20250630
PublicationDateYYYYMMDD 2025-06-30
PublicationDate_xml – month: 06
  year: 2025
  text: 20250630
  day: 30
PublicationDecade 2020
PublicationTitle Inteonet jeongbo hakoe nonmunji = Journal of Korean Society for Internet Information
PublicationTitleAlternate 인터넷정보학회논문지
PublicationYear 2025
Publisher 한국인터넷정보학회
Publisher_xml – name: 한국인터넷정보학회
SSID ssib053377390
ssib053835315
ssib001195163
ssib018233818
ssj0001908993
ssib036278810
ssib004698036
Score 2.3117478
Snippet 본 논문은 LSTM(Long Short-Term Memory) 모델을 활용한 주가 예측에서 추가적인 입력 변수인 기술적 지표 활용 여부가 모델 성능에 미치는 영향을 분석하고, 단방향 및...
This paper analyzes the effect of whether or not to utilize additional features on th model performance in stock price prediction using the LSTM(Long...
SourceID nrf
kisti
kiss
SourceType Open Website
Open Access Repository
Publisher
StartPage 111
SubjectTerms Bidirectional
Features
LSTM
RMSE
Stock price prediction
Unidirectional
단방향
양방향
주가 예측
컴퓨터학
평균 제곱근 오차
피처
Title 주가의 기술적 지표를 이용한 단방향·양방향 LSTM 모델의 주가 예측 분석
URI https://kiss.kstudy.com/ExternalLink/Ar?key=4182839
http://click.ndsl.kr/servlet/LinkingDetailView?cn=JAKO202520939605233&dbt=JAKO&org_code=O481&site_code=SS1481&service_code=01
https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART003222238
Volume 26
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
ispartofPNX 인터넷정보학회논문지, 2025, 26(3), , pp.111-119
journalDatabaseRights – providerCode: PRVEBS
  databaseName: Business Source Ultimate
  customDbUrl:
  eissn: 2287-1136
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001908993
  issn: 1598-0170
  databaseCode: AKVCP
  dateStart: 20141201
  isFulltext: true
  titleUrlDefault: https://search.ebscohost.com/login.aspx?authtype=ip,uid&profile=ehost&defaultdb=bsu
  providerName: EBSCOhost
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3Nb9MwFLfGdoEDAgZifEyRwKeoJXG-nKOTDo2NARIF7RaaLB1doUVdd-E0pB0mIQ47ME1ok4bQxMapBwQ77MSfs2b_A-85aRvGNA0uruM8__T8nl2_59jPhNyNbFZxIscshLGJV5jBSA9jWy84UVWLrIg5lRAX9Gce2ZPPzKlZa3boXCe3a2mpHRajtyeeK_kfrUIZ6BVPyf6DZvugUAB50C-koGFIz6RjOuFTYVDPpxOCehruWoASt0RdrsoijqVQxDkVMgMp11WZcyQ50OrUBQCPCguQ1AzBM2VGUOFKIguIVKTiQMgxA8jZOxur-ox6jqxjI-RfBOrDp-UZiSBEhsBLyGGO4-OtSZnhyD5kgFboEsGzKZf8QeqW8vY1LnA2G3FbXYCf-bCpvqzUm7HaaDZeLzUWaio1SmrOBp9utvBLRH7rarpECgjZQa38RoVMSq5kRzDKrUxInpYnAd49XTZCl3IsYQMHMS5l05mUgY9NSeGgKZ6eX4NhVm_DYDZq-nqQ0BYVpZ6uOL5CAE1im5kmQNlAjwwZPT6geqoSQbmfn5DwCKSeXq6STTK96SnOntyTpkJwEzG07kJ9sVYrIs9FZheNYr9uPvD4MYPgj9Dj9agWzDeDeisAB-tBoMOUwBjG2R1hjm2zYTIipp_7TwYmuA42-yCkG7ivBhqFvWewl_ACg_4cAd6G4xhu7hlcAiMzUeU6qfwwLc_J9ESRBg_DBt47oXlgW4HrtQjOJnpgNbAZG61qzmYsXyIXs46miHTkXiZD9eYVciEXAnSUvEi-HBx2lpOtDeVwv5Osbifb75Tk6_LR2mZ350BJtr4nn_aOPm4q3fe73c7e0frOr5_J-lqaVXBMKd1vu90P-4iQYinJxmqy_1np_lhJVraukvL9ibI_WchuPSnUueUWQrNSrboaq-o2N8D8jy3OXMswwdDXnNA1TFsa9aGM9ajZcTU2oTR0IrA0KxGLjWtkGAZVfJ0o3AD3ZM6uWJzDH7FrYgRgS5uzYyPEkEz6GBlFSQVv0rg2gQnKAn9pjIxLyQWNucVXwZSYfozyZZprQC0L1DlG7oBIZc84pYfcOBPVTXJ-MKBukeF2aym-DWZ-OxzPetZviozVsQ
linkProvider EBSCOhost
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%EC%A3%BC%EA%B0%80%EC%9D%98+%EA%B8%B0%EC%88%A0%EC%A0%81+%EC%A7%80%ED%91%9C%EB%A5%BC+%EC%9D%B4%EC%9A%A9%ED%95%9C+%EB%8B%A8%EB%B0%A9%ED%96%A5%C2%B7%EC%96%91%EB%B0%A9%ED%96%A5+LSTM+%EB%AA%A8%EB%8D%B8%EC%9D%98+%EC%A3%BC%EA%B0%80+%EC%98%88%EC%B8%A1+%EB%B6%84%EC%84%9D&rft.jtitle=Inteonet+jeongbo+hakoe+nonmunji+%3D+Journal+of+Korean+Society+for+Internet+Information&rft.au=%EB%A5%98%EC%A2%85%EC%9A%B0&rft.au=%EB%B0%B1%EA%B1%B4%ED%9D%AC&rft.au=%EB%82%A8%EC%B6%98%EC%84%B1&rft.date=2025-06-30&rft.pub=%ED%95%9C%EA%B5%AD%EC%9D%B8%ED%84%B0%EB%84%B7%EC%A0%95%EB%B3%B4%ED%95%99%ED%9A%8C&rft.issn=1598-0170&rft.spage=111&rft.epage=119&rft_id=info:doi/10.7472%2Fjksii.2025.26.3.111&rft.externalDBID=n%2Fa&rft.externalDocID=oai_kci_go_kr_ARTI_10732219
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1598-0170&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1598-0170&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1598-0170&client=summon