Learning Bermudans

24 Pages Posted: 5 May 2021

See all articles by Riccardo Aiolfi

Riccardo Aiolfi

Dipartimento di Fisica, Università degli Studi di Milano

Nicola Moreni

Intesa Sanpaolo, CIB Division, Global Markets

Marco Bianchetti

Intesa Sanpaolo - Financial and Market Risk Management; University of Bologna; AIFIRM - Associazione Italiana Financial Industry Risk Manager

Marco Scaringi

Intesa Sanpaolo - Financial and Market Risk Management

filippo fogliani

Intesa SanPaolo SpA - Financial and Market Risk Management Department

Date Written: April 30, 2021

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.

Keywords: Bermudan, Swaptions, Pricing, Interest Rates, Derivatives, Least Square, Monte Carlo, Hull-White model, G1++, Machine Learning, Supervised Learning, Neural Networks, Ridge, Support Vector Machine, Decision Tree, Random Forest, Gradient Boosted Regression Tree, K-Nearest Neighbours, Regression, Hedgi

JEL Classification: C45, C53, C63, G12

Suggested Citation

Aiolfi, Riccardo and Moreni, Nicola and Bianchetti, Marco and Scaringi, Marco and fogliani, filippo, Learning Bermudans (April 30, 2021). Available at SSRN: https://ssrn.com/abstract=3837499 or http://dx.doi.org/10.2139/ssrn.3837499

Riccardo Aiolfi (Contact Author)

Dipartimento di Fisica, Università degli Studi di Milano ( email )

Via Celoria, 16
Milano, 20133
Italy

Nicola Moreni

Intesa Sanpaolo, CIB Division, Global Markets

Largo R.Mattioli 3
P.O. BOX 8319
Milan, Milan 20121
Italy

Marco Bianchetti

Intesa Sanpaolo - Financial and Market Risk Management ( email )

Piazza P. Ferrari 10
Milan, 20121
Italy

University of Bologna ( email )

Piazza Scaravilli 2
Bologna, 40100
Italy

AIFIRM - Associazione Italiana Financial Industry Risk Manager ( email )

www.aifirm.it
Italy

Marco Scaringi

Intesa Sanpaolo - Financial and Market Risk Management ( email )

Piazza P. Ferrari 10
Milan, 20121
Italy

Filippo Fogliani

Intesa SanPaolo SpA - Financial and Market Risk Management Department ( email )

Milan
Italy

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

Paper statistics

Downloads
69
Abstract Views
296
rank
416,361
PlumX Metrics