An analysis of linear regression and neural networks approximation for the pricing of swing options

TL;DR

This paper compares linear regression and neural networks for approximating swing option prices, proving convergence of the methods and analyzing their practical Monte Carlo-based implementations.

Contribution

It establishes convergence results for both linear regression and neural network approaches in swing option pricing, including practical Monte Carlo approximation analysis.

Findings

Both methods converge to the true swing price as the approximation complexity increases.

A convergence rate of order 1/√N is established for linear regression with Monte Carlo.

Neural networks provide a viable alternative with similar convergence properties.

Abstract

Linear regression, firstly introduced for the pricing of American-style options, has since been expanded to include swing options pricing. Swing options price may be viewed as the solution to a Backward Dynamic Programming Principle, which involves a conditional expectation known as the continuation value. The approximation of the continuation value using linear regression involves two levels of approximation. First, the continuation value is replaced by an orthogonal projection over a subspace spanned by a finite set of $m$ squared-integrable functions yielding a first approximation $V^m$ of the swing value function. In this paper, we prove that, with well-chosen regression functions, $V^m$ converges to the swing actual price $V$ as $m \to + \infty$. A similar result is proved when classic regression functions are replaced by neural networks. For both methods (linear regression and neural networks), we analyze the second level of approximation involving practical computation of the swing price using Monte Carlo simulations and yielding an approximation $V^{m, N}$ (where $N$ denotes the Monte Carlo sample size). Especially, we prove that $V^{m, N} \to V^m$ as $N \to + \infty$ for both methods and using a Hilbert basis assumption in the linear regression. Besides, a convergence rate of order $\mathcal{O}\big(\frac{1}{\sqrt{N}} \big)$ is proved in the linear regression case.