Learning Bermudans

TL;DR

This paper introduces a novel approach for pricing Bermudan Swaptions using supervised learning algorithms, which improves computational efficiency and provides insights into key pricing factors.

Contribution

The paper proposes an original supervised learning-based method for Bermudan Swaption pricing, linking it to underlying European Swaptions and analyzing various algorithms' performance.

Findings

Supervised learning algorithms are reliable and fast for Bermudan Swaption pricing.

Best algorithms identified are Ridge, ANN, and Gradient Boosted Regression Tree.

Feature importance analysis highlights the maximum underlying European Swaption as the main pricing factor.

Abstract

American and Bermudan-type financial instruments are often priced with specific Monte Carlo techniques whose efficiency critically depends on the effective dimensionality of the problem and the available computational power. In our work we focus on Bermudan Swaptions, well-known interest rate derivatives embedded in callable debt instruments or traded in the OTC market for hedging or speculation purposes, and we adopt an original pricing approach based on Supervised Learning (SL) algorithms. In particular, we link the price of a Bermudan Swaption to its natural hedges, i.e. the underlying European Swaptions, and other sound financial quantities through SL non-parametric regressions. We test different algorithms, from linear models to decision tree-based models and Artificial Neural Networks (ANN), analyzing their predictive performances. All the SL algorithms result to be reliable and fast, allowing to overcome the computational bottleneck of standard Monte Carlo simulations; the best performing algorithms for our problem result to be Ridge, ANN and Gradient Boosted Regression Tree. Moreover, using feature importance techniques, we are able to rank the most important driving factors of a Bermudan Swaption price, confirming that the value of the maximum underlying European Swaption is the prevailing feature.