메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

논문 기본 정보

자료유형
학술저널
저자정보
최인수 (한국과학기술원) 김우창 (한국과학기술원)
저널정보
대한산업공학회 대한산업공학회지 대한산업공학회지 제48권 제4호
발행연도
2022.8
수록면
340 - 354 (15page)
DOI
10.7232/JKIIE.2022.48.4.340

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

초록· 키워드

오류제보하기
The stock market has been extensively studied as one of the important research areas of economics and finance. In particular, research on analyzing and predicting stock markets based on stock price and rate of change data is the most active topic in the financial sector, and specifically, predicting stock prices and markets as a whole is one of the important factors for investors to establish optimal investment strategies. In this study, a causal network was constructed based on the information flow of major financial market indices using the concept of transfer entropy. In addition, the financial market was analyzed using the configured network, and the predictive power of KOSPI"s fluctuation could be almost maintained using a cluster-based smaller number of whole data when predicting the global financial market index based on the fluctuation of information flows. To conduct this experiment, transfer entropy, which measures the amount of reduction in information uncertainty, was used as an indicator of measuring causal relationships. Specifically, an information flow network was constructed using efficient transfer entropy, an effective indicator in adjusting the finite size effect that may occur when measuring transfer entropy. In other words, we analyzed the causal relationships between global financial indices and predicted KOSPI fluctuation using effective transfer entropy. As a result, it was confirmed that the financial market index could be analyzed using a causal network using efficient transfer entropy, and the improved prediction results could be confirmed using fewer data columns in predicting fluctuations in the domestic financial market using the configured network.

목차

1. 서론
2. 데이터 및 연구 방법론
3. 연구 방법론
4. 실험 결과
5. 결론
참고문헌

참고문헌 (69)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

이 논문의 저자 정보

이 논문과 함께 이용한 논문

최근 본 자료

전체보기

댓글(0)

0

UCI(KEPA) : I410-ECN-0101-2022-530-001628510