Pricing options on flow forwards by neural networks in Hilbert space

21 Pages Posted: 28 Mar 2022

See all articles by Fred Espen Benth

Fred Espen Benth

University of Oslo

Nils Detering

University of California, Santa Barbara (UCSB)

Luca Galimberti

Norwegian University of Science and Technology (NTNU)

Date Written: February 23, 2022

Abstract

We propose a new methodology for pricing options on flow forwards by applying infinite-dimensional neural networks. We recast the pricing problem as an optimization problem in a Hilbert space of real-valued function on the positive real line, which is the state space for the term structure dynamics. This optimization problem is solved by facilitating a novel feedforward neural network architecture designed for approximating continuous functions on the state space. The proposed neural net is built upon the basis of the Hilbert space. We provide an extensive case study that shows excellent numerical efficiency, with superior performance over that of a classical neural net trained on sampling the term structure curves.

Keywords: flow forwards derivatives, term structure, neural networks

JEL Classification: C61,G13

Suggested Citation

Benth, Fred Espen and Detering, Nils and Galimberti, Luca, Pricing options on flow forwards by neural networks in Hilbert space (February 23, 2022). Available at SSRN: https://ssrn.com/abstract=4042049 or http://dx.doi.org/10.2139/ssrn.4042049

Fred Espen Benth

University of Oslo ( email )

Center of Mathematics for Applications
Oslo, N-0317
Norway

Nils Detering (Contact Author)

University of California, Santa Barbara (UCSB) ( email )

South Hall 5504

Luca Galimberti

Norwegian University of Science and Technology (NTNU) ( email )

Høgskoleringen
Trondheim NO-7491, 7491
Norway

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
58
Abstract Views
267
Rank
681,507
PlumX Metrics