DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 김아현 | - |
dc.contributor.author | Park, Min-Woo | - |
dc.contributor.author | 박민우 | - |
dc.date.accessioned | 2024-07-26T19:31:08Z | - |
dc.date.available | 2024-07-26T19:31:08Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1047718&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321017 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 금융공학프로그램, 2023.8,[iii, 39 p. :] | - |
dc.description.abstract | This paper analyzes the performance of pairs trading constructed via three unsupervised learnings in the Korean market. In addition to traditional pairs trading, it incorporates firm characteristics to identify more robust pairs. The result reveals that two of the three clustering algorithms tend to outperform the benchmark KOSPI even after accounting for the risk. Long-short equally weighted portfolios via k-means clustering performs best in the Korean market with an annualized mean return of 34% and Sharpe Ratio of 0.667. Moreover, utilizing firm characteristics enhance the performance of the strategy by improving return and reducing volatility at the same time. However, in the robustness check, it reveals some limitations such as profitability differs variously according to the selection of hyperparameters. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 페어 트레이딩▼a클러스터링▼a비지도학습▼aK-means 군집▼aDBSCAN▼a병합 군집 | - |
dc.subject | Pairs trading▼aClustering▼aUnsupervised learning▼aK-means clustering▼aDBSCAN▼aAgglomerative clustering | - |
dc.title | Performance analysis of pairs trading using firm characteristics via clustering methods in the Korean stock market | - |
dc.title.alternative | 한국 주식 시장에서 기업 특성과 군집화 방법을 통한 페어 트레이딩 전략 성과 분석 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :금융공학프로그램, | - |
dc.contributor.alternativeauthor | Kim, Ahhyoun | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.