본문 바로가기 주메뉴 바로가기
22대 대한민국 국회 국회정보길라잡이 국회의원검색
회원가입 로그인
HOME

정보검색

소장정보 검색

국회도서관 홈으로 정보검색 소장정보 검색

결과 내 검색

동의어 포함

고급검색

인명/단체명

저자정보 상세정보
인명/단체명을 입력하세요.

키워드

  • 대표어

  • 외국어

-

초록보기

본 연구는 기술적 지표를 활용하여 투자 비중을 동적으로 조정하는 머신러닝 기반 자산 배분 전략을 개발하는 것을 목적으로 한다. Bollinger Band와 CCI(Commodity Channel Index)를 기반으로 한 파라메트릭 구조를 통해 시장 변화에 유연하게 대응할 수 있는 전략을 설계하였다. 전략의 파라미터 최적화를 위해 Differential Evolution(DE), Powell, L-BFGS-B, TNC, COBYLA, TRUST-CONSTR 등 총 6가지 최적화 알고리즘을 적용하였으며, 과거 ETF 데이터를 바탕으로 반복 실험을 수행하였다. 각 알고리즘은 연간 실현 수익률, 수익 안정성, 과적합 지표 등을 기준으로 평가되었으며, 이 중 DE 알고리즘은 모든 기준에서 가장 우수한 성과를 보였다. DE는 탐색 공간을 효과적으로 탐색하고 지역 최적값에 빠지지 않는 특성으로 인해 뛰어난 일반화 성능과 낮은 과적합 수준을 보여주었다. 본 연구 결과는 기술적 지표와 전역 최적화 기법을 결합한 전략이 동적 금융 환경에서도 강건한 투자 전략으로 활용될 수 있음을 시사한다.

This study aims to develop a machine-learning-based asset allocation strategy that dynamically adjusts investment weights using technical indicators. By employing a parametric structure grounded in Bollinger Bands and the Commodity Channel Index (CCI), the strategy offers flexible responses to market changes. Several optimization algorithms, including Differential Evolution (DE), Powell, L-BFGS-B, TNC, COBYLA, and TRUST-CONSTR, were applied to tune the strategy parameters using historical ETF data. Each optimizer was evaluated through repeated simulations, and the models were assessed based on annual realized profits, return stability, and overfitting metrics. Among them, DE consistently delivered superior performance, demonstrating strong generalization and low levels of overfitting. These outcomes are attributed to DE’s ability to escape local optima and effectively explore the search space. These results indicate that combining global optimization with technical indicators enables robust, data-driven investment strategies that are adaptable to dynamic financial environments.

권호기사

권호기사 목록 테이블로 기사명, 저자명, 페이지, 원문, 기사목차 순으로 되어있습니다.
기사명 저자명 페이지 원문 목차
Performance comparison of RDB and NoSQL in real-time data processing systems based on Spring WebFlux Minsol Kim, Jongha Kim, Sehoon Lee p. 1-10

Energy-adaptive approximate computing scheme for efficient federated learning in energy-harvesting AIoT systems Ikjune Yoon, Dong Kun Noh p. 11-19

Flow-based QoS routing optimization using AI-driven traffic prediction scheme Moon-Sik Kang p. 21-32

Design and implementation of an AI-based emotion analysis system through music and vocal separation Byong-Kwon Lee p. 33-39

Can MLLMs see the market? Evaluating pattern reasoning in real-world financial charts Eun Hong Park, Ji Hoon Park, Ha Young Kim p. 41-51

Machine-learning-based optimization of ETF split trading strategies with technical indicators Dongwon Lee p. 53-63

(A) dual-band radiometric framework for passive infrared ranging Jeong-Hyeon Moon, Seungha Kim, BongJun Choi, Heeduk Park p. 65-77

Design of a RAG-based Q&A system for university academic administration assistants Jae-Kwang Oh, Soo Kyun Kim p. 79-86

Design and evaluation of LLM-based conversational agents for diagnosing science learning difficulties Tae-Ho Min p. 87-96

Social service needs of older adults with disabilities : a comparison by timing of disability onset Daeun Oh p. 97-104

Effects of 8 weeks resistance exercise on body composition, 1RM, cancer related fatigue and quality of life in cancer survivors Min-Su Choi, Jin-Wook Lee, Yong-Hyun Byun p. 105-114

(The) effect of psychological interventions on anxiety and depression in parents of children with cancer : a meta-analysis of randomized controlled trials Young-Ran Yeun p. 115-128

Analysis and comparison of single-phase and interleaved two-phase LLC resonant converter topologies for EV battery charging application Tae-Seok Kang, Hyun-Gyu Koh, Yoo-Seop Kim, Yeong-Jun Choi p. 129-136

(The) loss analysis of three-phase wye-wye and delta-delta LLC resonant converter under the leg-open fault Hyun-Jin Jin, Jihun So, Yoo-Seop Kim, Yeong-Jun Choi p. 137-145

Antecedents and consequences of technostress in generative AI : focused on ChatGPT users Yujin Kim, Hyung-Seok Lee p. 147-157

(A) study on the information adoption process in ChatGPT Yujin Kim, Hyung-Seok Lee p. 159-169

Item-attribute-based semantic similarity for data sparsity in collaborative filtering Soojung Lee p. 171-179

Analysis of the efficiency of foreign direct investment in China Jiangsu province by manufacturing industry Sang-Wook Kim p. 181-188

Exploring the design direction of generative AI-based web systems to support question-centered classes So-jeong Choi, Kwi-hoon Kim p. 189-201

Exploring factors affecting the academic adjustment of multicultural adolescents in high school : focusing on living environment factors Kwan-Sook Kim, Yong-Seob Kim, Chi-Won Choi p. 203-212

추천서가 (다양한 추천 자료를 만나보세요)

권호기사보기

권호기사 목록 테이블로 기사명, 저자명, 페이지, 원문, 기사목차 순으로 되어있습니다.
기사명 저자명 페이지 원문 기사목차

권호

기사명 원문보기 기사목차
닫기