Pricing path-dependent exotic options with flow-based generative networks

Hyun Gyoon Kim; Se Jin Kwon; Jeong Hoon Kim; Jeonggyu Huh

doi:10.1016/j.asoc.2022.109049

Pricing path-dependent exotic options with flow-based generative networks

Hyun Gyoon Kim, Se Jin Kwon, Jeong Hoon Kim, Jeonggyu Huh

Department of Mathematics

Research output: Contribution to journal › Article › peer-review

Abstract

In this study, we aim to significantly reduce the computational time for pricing path-dependent exotic options using a flow-based generative model called RealNVP (Dinh et al., 2016). The flow-based generative network learns simulated large-scale two-dimensional random states based on two stochastic volatility (SV) models. As a result, the generative network can efficiently simulate the random states within a short time. Furthermore, they can provide explicit probability density functions for the SV models due to the unique advantage of flow-based generative models. These lead to fairly exact option prices being achieved by simulating random states with the network or integrating option payoffs for the network-based density. Finally, we compare the network-based prices with those of naive Monte-Carlo simulation in terms of accuracy and time cost to show the superior performance of the proposed method.

Original language	English
Article number	109049
Journal	Applied Soft Computing
Volume	124
DOIs	https://doi.org/10.1016/j.asoc.2022.109049
Publication status	Published - 2022 Jul

Bibliographical note

Funding Information:
We thank the anonymous reviewers for careful reading our manuscript and giving constructive suggestions. Jeonggyu Huh received financial support from the National Research Foundation of Korea (Grant No. NRF-2019R1F1A1058352). This work was supported by Artificial intelligence industrial convergence cluster development project funded by the Ministry of Science and ICT(MSIT, Korea) & Gwangju Metropolitan City. Jeong-Hoon Kim was supported by the National Research Foundation of KoreaNRF2021R1A2C1004080.

Funding Information:
We thank the anonymous reviewers for careful reading our manuscript and giving constructive suggestions. Jeonggyu Huh received financial support from the National Research Foundation of Korea (Grant No. NRF-2019R1F1A1058352 ). This work was supported by Artificial intelligence industrial convergence cluster development project funded by the Ministry of Science and ICT(MSIT, Korea) & Gwangju Metropolitan City. Jeong-Hoon Kim was supported by the National Research Foundation of Korea NRF2021R1A2C1004080 .

Publisher Copyright:
© 2022 Elsevier B.V.

All Science Journal Classification (ASJC) codes

Software

Access to Document

10.1016/j.asoc.2022.109049

Cite this

@article{4058e726ea504768be679b5cd4774890,

title = "Pricing path-dependent exotic options with flow-based generative networks",

abstract = "In this study, we aim to significantly reduce the computational time for pricing path-dependent exotic options using a flow-based generative model called RealNVP (Dinh et al., 2016). The flow-based generative network learns simulated large-scale two-dimensional random states based on two stochastic volatility (SV) models. As a result, the generative network can efficiently simulate the random states within a short time. Furthermore, they can provide explicit probability density functions for the SV models due to the unique advantage of flow-based generative models. These lead to fairly exact option prices being achieved by simulating random states with the network or integrating option payoffs for the network-based density. Finally, we compare the network-based prices with those of naive Monte-Carlo simulation in terms of accuracy and time cost to show the superior performance of the proposed method.",

author = "Kim, {Hyun Gyoon} and Kwon, {Se Jin} and Kim, {Jeong Hoon} and Jeonggyu Huh",

note = "Funding Information: We thank the anonymous reviewers for careful reading our manuscript and giving constructive suggestions. Jeonggyu Huh received financial support from the National Research Foundation of Korea (Grant No. NRF-2019R1F1A1058352). This work was supported by Artificial intelligence industrial convergence cluster development project funded by the Ministry of Science and ICT(MSIT, Korea) & Gwangju Metropolitan City. Jeong-Hoon Kim was supported by the National Research Foundation of KoreaNRF2021R1A2C1004080. Funding Information: We thank the anonymous reviewers for careful reading our manuscript and giving constructive suggestions. Jeonggyu Huh received financial support from the National Research Foundation of Korea (Grant No. NRF-2019R1F1A1058352 ). This work was supported by Artificial intelligence industrial convergence cluster development project funded by the Ministry of Science and ICT(MSIT, Korea) & Gwangju Metropolitan City. Jeong-Hoon Kim was supported by the National Research Foundation of Korea NRF2021R1A2C1004080 . Publisher Copyright: {\textcopyright} 2022 Elsevier B.V.",

year = "2022",

month = jul,

doi = "10.1016/j.asoc.2022.109049",

language = "English",

volume = "124",

journal = "Applied Soft Computing",

issn = "1568-4946",

publisher = "Elsevier BV",

}

TY - JOUR

T1 - Pricing path-dependent exotic options with flow-based generative networks

AU - Kim, Hyun Gyoon

AU - Kwon, Se Jin

AU - Kim, Jeong Hoon

AU - Huh, Jeonggyu

N1 - Funding Information: We thank the anonymous reviewers for careful reading our manuscript and giving constructive suggestions. Jeonggyu Huh received financial support from the National Research Foundation of Korea (Grant No. NRF-2019R1F1A1058352). This work was supported by Artificial intelligence industrial convergence cluster development project funded by the Ministry of Science and ICT(MSIT, Korea) & Gwangju Metropolitan City. Jeong-Hoon Kim was supported by the National Research Foundation of KoreaNRF2021R1A2C1004080. Funding Information: We thank the anonymous reviewers for careful reading our manuscript and giving constructive suggestions. Jeonggyu Huh received financial support from the National Research Foundation of Korea (Grant No. NRF-2019R1F1A1058352 ). This work was supported by Artificial intelligence industrial convergence cluster development project funded by the Ministry of Science and ICT(MSIT, Korea) & Gwangju Metropolitan City. Jeong-Hoon Kim was supported by the National Research Foundation of Korea NRF2021R1A2C1004080 . Publisher Copyright: © 2022 Elsevier B.V.

PY - 2022/7

Y1 - 2022/7

N2 - In this study, we aim to significantly reduce the computational time for pricing path-dependent exotic options using a flow-based generative model called RealNVP (Dinh et al., 2016). The flow-based generative network learns simulated large-scale two-dimensional random states based on two stochastic volatility (SV) models. As a result, the generative network can efficiently simulate the random states within a short time. Furthermore, they can provide explicit probability density functions for the SV models due to the unique advantage of flow-based generative models. These lead to fairly exact option prices being achieved by simulating random states with the network or integrating option payoffs for the network-based density. Finally, we compare the network-based prices with those of naive Monte-Carlo simulation in terms of accuracy and time cost to show the superior performance of the proposed method.

AB - In this study, we aim to significantly reduce the computational time for pricing path-dependent exotic options using a flow-based generative model called RealNVP (Dinh et al., 2016). The flow-based generative network learns simulated large-scale two-dimensional random states based on two stochastic volatility (SV) models. As a result, the generative network can efficiently simulate the random states within a short time. Furthermore, they can provide explicit probability density functions for the SV models due to the unique advantage of flow-based generative models. These lead to fairly exact option prices being achieved by simulating random states with the network or integrating option payoffs for the network-based density. Finally, we compare the network-based prices with those of naive Monte-Carlo simulation in terms of accuracy and time cost to show the superior performance of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=85131459987&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85131459987&partnerID=8YFLogxK

U2 - 10.1016/j.asoc.2022.109049

DO - 10.1016/j.asoc.2022.109049

M3 - Article

AN - SCOPUS:85131459987

SN - 1568-4946

VL - 124

JO - Applied Soft Computing

JF - Applied Soft Computing

M1 - 109049

ER -

Pricing path-dependent exotic options with flow-based generative networks

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this