DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kang, Jangkoo | - |
dc.contributor.advisor | 강장구 | - |
dc.contributor.author | Lee, Dong Hee | - |
dc.date.accessioned | 2022-04-15T07:57:08Z | - |
dc.date.available | 2022-04-15T07:57:08Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=963802&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/294936 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 금융공학프로그램, 2021.8,[iii, 39 p. :] | - |
dc.description.abstract | Attempts have been made to incorporate advanced machine learning techniques to handle financial data due to their non-linearity, high-dimensionality, and non-stationarity. However, even with wider applications in finance, such techniques have given limited insights to investors due to their black-box nature. In addition, typical portfolio optimization through machine learning takes two steps, return prediction and weight assignment, which magnify optimization error. To overcome aforementioned limitation, this paper implements deep reinforcement learning-based portfolio optimization model introduced by Cong, Tang, Wang, and Zhang (2020) to the Korean stock market. The model consisted of Transformer Encoder and Cross-Asset Attention Network optimizes Sharpe ratio of directly constructed portfolio. The portfolio exhibits outstanding out of sample performance even under various restrictions, including transaction costs, and short sale constraints. Lastly, the interpretation of the model is achieved by replicating policy network of the model into second degree polynomial. Through dominant feature ranking and feature dynamic analysis, it is concluded that the model depicts SG&A to sales ratio as one of the most dominant features, and it tends to put more weights on profitability characteristics during earlier months in the test period from 2006 to 2020 and value characteristics during the later months. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Machine learning▼aReinforcement learning▼aPortfolio theory▼aPortfolio optimization▼aAI interpretation | - |
dc.subject | 머신러닝▼a강화학습▼a포트폴리오 이론▼a포트폴리오 최적화▼a인공지능 해석 | - |
dc.title | Portfolio construction through reinforcement learning: an empirical study on the Korean stock market via interpretable AI | - |
dc.title.alternative | 강화학습을 활용한 포트폴리오 구성: 인공지능 해석을 통한 한국 주식시장 실증분석 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :금융공학프로그램, | - |
dc.contributor.alternativeauthor | 이동희 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.