View : 321 Download: 0

Full metadata record

DC Field Value Language
dc.contributor.advisor안재윤-
dc.contributor.author이원민-
dc.creator이원민-
dc.date.accessioned2018-03-06T16:30:44Z-
dc.date.available2018-03-06T16:30:44Z-
dc.date.issued2018-
dc.identifier.otherOAK-000000147822-
dc.identifier.urihttp://dcollection.ewha.ac.kr/common/orgView/000000147822en_US
dc.identifier.urihttp://dspace.ewha.ac.kr/handle/2015.oak/240384-
dc.description.abstractLeast Squares Monte Carlo (LSMC) method is common method of risk assessment in financial sector. While the performance of LSMC method is known to be relatively good in moderate situation, it may not be well suited for high-dimensional data, mainly due to the number of explanatory variables are increased exponentially as the risk factors considered in the model increase. In this study, we provide modified LSMC algorithm where the simple least square technique is replaced by random forest method, which is known to be efficient at handling high dimensional non-linear setting. Simulation study is accompanied to assess the performance of the proposed method.;금융 시장에서 옵션과 같은 파생상품의 가격 계산 및 금융 위험 관리는 중요한 주제 중의 하나이다. 이를 추정하는 대표적인 방법중의 하나는 최소자승 MC (Least-Squares Monte Carlo) 방법이다. 이 방법의 장점은 MC 방법의 정확성과 유사하면서 계산 시간을 줄일 수 있다는 것이다. 하지만 여러 개의 위험 요소를 고려하는 경우, 즉 고차원의 경우에서는 최소 자승 MC의 추정이 까다롭다. 본 논문에서는 최소자승 MC 모형에서 선형 회귀 모형을 랜덤 포레스트로 대체한 모형을 제시하고, 제시한 모형의 성능을 모의실험으로 평가하여 본다.-
dc.description.tableofcontentsⅠ Introduction 1 Ⅱ The LSMC algorithm 2 A. Nested Scenarios 2 B. Lest-squares Monte Carlo (LSMC) approach 3 C. Issues on LSMC algorithm 7 Ⅲ Modification of LSMC using tree-based algorithm 10 A. Tree-based algorithm 10 B. Modification of LSMC using tree-based algorithm 11 Ⅳ Simulation study 12 A. Simulation frame work 12 B. Result of simulation study 13 Ⅴ Conclusion 23 Bibliography 24 Appendix 25 Abstract (in Korean) 29-
dc.formatapplication/pdf-
dc.format.extent1288294 bytes-
dc.languageeng-
dc.publisher이화여자대학교 대학원-
dc.subject.ddc500-
dc.titleModification of Least Squares Monte Carlo Method in Quantitative Risk Management Using Tree-Based Method-
dc.typeMaster's Thesis-
dc.format.pageiv, 29 p.-
dc.contributor.examiner신동완-
dc.contributor.examiner이외숙-
dc.contributor.examiner안재윤-
dc.identifier.thesisdegreeMaster-
dc.identifier.major대학원 통계학과-
dc.date.awarded2018.2-
Appears in Collections:
일반대학원 > 통계학과 > Theses_Master
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE