Feynman-Kac Derivatives Pricing on the Full Forward Curve

TL;DR

This paper presents a neural network-based PDE approach for arbitrage-free, fast, and accurate pricing of path-dependent interest rate derivatives, outperforming traditional Monte Carlo methods in speed and efficiency.

Contribution

Introduces a novel neural network method (FINNs) to solve PDEs for interest rate derivatives, enabling rapid, accurate pricing without Monte Carlo simulation.

Findings

FINNs achieve pricing accuracy within 0.04 to 0.07 cents per dollar.

Pricing speed is 300,000 to 4.5 million times faster than Monte Carlo.

Greeks are computed automatically at zero additional cost.

Abstract

This paper introduces a no-arbitrage, Monte Carlo-free approach to pricing path-dependent interest rate derivatives. The Heath-Jarrow-Morton model gives arbitrage-free contingent claims prices but is infinite-dimensional, making traditional numerical methods computationally prohibitive. To make the problem computationally tractable, I cast the stochastic pricing problem as a deterministic partial differential equation (PDE). Finance-Informed Neural Networks (FINNs) solve this PDE directly by minimizing violations of the differential equation and boundary condition, with automatic differentiation efficiently computing the exact derivatives needed to evaluate PDE terms. FINNs achieve pricing accuracy within 0.04 to 0.07 cents per dollar of contract value compared to Monte Carlo benchmarks. Once trained, FINNs price caplets in a few microseconds regardless of dimension, delivering speedups ranging from 300,000 to 4.5 million times faster than Monte Carlo simulation as the state space discretization of the forward curve grows from 10 to 150 nodes. The major Greeks-theta and curve deltas-come for free, computed automatically during PDE evaluation at zero marginal cost, whereas Monte Carlo requires complete re-simulation for each sensitivity. The framework generalizes naturally beyond caplets to other path-dependent derivatives-caps, swaptions, callable bonds-requiring only boundary condition modifications while retaining the same core PDE structure.