A Functional Approach to Accelerating Monte Carlo based American Option Pricing

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Standard

A Functional Approach to Accelerating Monte Carlo based American Option Pricing. / Pawlak, Wojciech Michal; Elsman, Martin; Oancea, Cosmin Eugen.

IFL 2019: Proceedings of the 28th Symposium on the Implementation and Application of Functional Programming Languages. Association for Computing Machinery, 2021. s. 1-12 5.

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Harvard

Pawlak, WM, Elsman, M & Oancea, CE 2021, A Functional Approach to Accelerating Monte Carlo based American Option Pricing. i IFL 2019: Proceedings of the 28th Symposium on the Implementation and Application of Functional Programming Languages., 5, Association for Computing Machinery, s. 1-12, 28th Symposium on the Implementation and Application of Functional Programming Languages . IFL 2019, Singapore, Singapore, 19/09/2019. https://doi.org/10.1145/3412932.3412937

APA

Pawlak, W. M., Elsman, M., & Oancea, C. E. (2021). A Functional Approach to Accelerating Monte Carlo based American Option Pricing. I IFL 2019: Proceedings of the 28th Symposium on the Implementation and Application of Functional Programming Languages (s. 1-12). [5] Association for Computing Machinery. https://doi.org/10.1145/3412932.3412937

Vancouver

Pawlak WM, Elsman M, Oancea CE. A Functional Approach to Accelerating Monte Carlo based American Option Pricing. I IFL 2019: Proceedings of the 28th Symposium on the Implementation and Application of Functional Programming Languages. Association for Computing Machinery. 2021. s. 1-12. 5 https://doi.org/10.1145/3412932.3412937

Author

Pawlak, Wojciech Michal ; Elsman, Martin ; Oancea, Cosmin Eugen. / A Functional Approach to Accelerating Monte Carlo based American Option Pricing. IFL 2019: Proceedings of the 28th Symposium on the Implementation and Application of Functional Programming Languages. Association for Computing Machinery, 2021. s. 1-12

Bibtex

@inproceedings{192d67dafc9d4bf28e8d1673d1944722,
title = "A Functional Approach to Accelerating Monte Carlo based American Option Pricing",
abstract = "We study the feasibility and performance efficiency of expressing a complex financial numerical algorithm with high-level functional parallel constructs. The algorithm we investigate is a least-square regression-based Monte-Carlo simulation for pricing American options. We propose an accelerated parallel implementation in Futhark, a high-level functional data-parallel language. The Futhark language targets GPUs as the compute platform and we achieve a performance comparable to, and in particular cases up to 2.5X better than, an implementation optimised by NVIDIA CUDA engineers. In absolute terms, we can price a put option with 1 million simulation paths and 100 time steps in 17 ms on a NVIDIA Tesla V100 GPU. Furthermore, the high-level functional specification is much more accessible to the financial-domain experts than the low-level CUDA code, thus promoting code maintainability and facilitating algorithmic changes.",
author = "Pawlak, {Wojciech Michal} and Martin Elsman and Oancea, {Cosmin Eugen}",
year = "2021",
doi = "10.1145/3412932.3412937",
language = "English",
pages = "1--12",
booktitle = "IFL 2019: Proceedings of the 28th Symposium on the Implementation and Application of Functional Programming Languages",
publisher = "Association for Computing Machinery",
note = "null ; Conference date: 19-09-2019",

}

RIS

TY - GEN

T1 - A Functional Approach to Accelerating Monte Carlo based American Option Pricing

AU - Pawlak, Wojciech Michal

AU - Elsman, Martin

AU - Oancea, Cosmin Eugen

PY - 2021

Y1 - 2021

N2 - We study the feasibility and performance efficiency of expressing a complex financial numerical algorithm with high-level functional parallel constructs. The algorithm we investigate is a least-square regression-based Monte-Carlo simulation for pricing American options. We propose an accelerated parallel implementation in Futhark, a high-level functional data-parallel language. The Futhark language targets GPUs as the compute platform and we achieve a performance comparable to, and in particular cases up to 2.5X better than, an implementation optimised by NVIDIA CUDA engineers. In absolute terms, we can price a put option with 1 million simulation paths and 100 time steps in 17 ms on a NVIDIA Tesla V100 GPU. Furthermore, the high-level functional specification is much more accessible to the financial-domain experts than the low-level CUDA code, thus promoting code maintainability and facilitating algorithmic changes.

AB - We study the feasibility and performance efficiency of expressing a complex financial numerical algorithm with high-level functional parallel constructs. The algorithm we investigate is a least-square regression-based Monte-Carlo simulation for pricing American options. We propose an accelerated parallel implementation in Futhark, a high-level functional data-parallel language. The Futhark language targets GPUs as the compute platform and we achieve a performance comparable to, and in particular cases up to 2.5X better than, an implementation optimised by NVIDIA CUDA engineers. In absolute terms, we can price a put option with 1 million simulation paths and 100 time steps in 17 ms on a NVIDIA Tesla V100 GPU. Furthermore, the high-level functional specification is much more accessible to the financial-domain experts than the low-level CUDA code, thus promoting code maintainability and facilitating algorithmic changes.

U2 - 10.1145/3412932.3412937

DO - 10.1145/3412932.3412937

M3 - Article in proceedings

SP - 1

EP - 12

BT - IFL 2019: Proceedings of the 28th Symposium on the Implementation and Application of Functional Programming Languages

PB - Association for Computing Machinery

Y2 - 19 September 2019

ER -

ID: 258660593