Deep learning with BSDE for pricing ELS
- 주제(키워드) Deep learning , ELS pricing , partial differential equation , backward stochastic differential equation , barrier option
- 주제(DDC) 332
- 발행기관 아주대학교
- 지도교수 민찬호
- 발행년도 2022
- 학위수여년월 2022. 8
- 학위명 석사
- 학과 및 전공 일반대학원 금융공학과
- 실제URI http://www.dcollection.net/handler/ajou/000000032097
- 본문언어 영어
- 저작권 아주대학교 논문은 저작권에 의해 보호받습니다.
초록/요약
Option price is solved by partial differential equations with specific terminal conditions. In this case, the PDE can be reformulated to BSDE. Recently, deep learning technology has been applied to evaluate the value of options using the BSDE approach. This technique is used as a method of learning the slope of a specific variable to solve BSDE including terminal conditions. In this paper, it proposes a method to evaluate the value of ELS through deep learning using BSDE algorithms and Brownian Bridge probability.
more목차
I. Introduction 1
II. Theoretical Background 1
1. Basic framework of DeepBSDE 1
2. Extension framework to solve ELS 4
3. Monte Carlo Simulation and Finite difference method 6
III. Empirical Results 8
1. Structure of Deep Neural Network 8
2. Test Results 9
IV. Conclusions 12
References 13