The Mathematical Institute, University of Oxford, Eprints Archive

Optimised Importance Sampling in Multilevel Monte Carlo

Gasparotto, Riccardo (2015) Optimised Importance Sampling in Multilevel Monte Carlo. Masters thesis, oxford university.



This dissertation explores the remarkable variance reduction effects that can be achieved combining Multilevel Monte Carlo and Importance Sampling. The analysis is conducted within a Black-Scholes framework, focusing on pricing deep out-of-the-money options. Particular attention is addressed to the choice of the Importance Sampling measure and to the optimisation of its parameters. Numerical results show that the combination of the two methods significantly outperforms both techniques if applied separately.

Key words: Monte Carlo, Multilevel Monte Carlo, Option Pricing, Importance Sampling, Variance Reduction

Item Type:Thesis (Masters)
Subjects:H - N > Mathematics education
Research Groups:Mathematical and Computational Finance Group
ID Code:1898
Deposited By: Laura Auger
Deposited On:08 Sep 2015 06:41
Last Modified:08 Sep 2015 06:41

Repository Staff Only: item control page