Monte Carlo simulation
Being particular about calibration
Following previous work on the calibration of multi-factor local stochastic volatility models to market smiles, Julien Guyon and Pierre Henry-Labordère show how to calibrate exactly any such model. Their approach, based on McKean’s particle method,…
Why insurers are turning to the least squares Monte Carlo modelling technique
The Monte Carlo method
Right Laplace, right time
Right Laplace, right time
A new breed of copulas for risk and portfolio management
A new breed of copulas for risk and portfolio management
Cutting edge introduction
Be discrete
Random grids
Random grids
Real-time counterparty credit risk management in Monte Carlo
Real-time counterparty credit risk management in Monte Carlo
Technology innovation of the year
Technology innovation of the year
Technology vendor rankings 2011: The results
Technology triumphs
Stressed in Monte Carlo
Stressed in Monte Carlo
Sponsored statement: Capitects
Multi-period portfolio optimisation for structured investment strategies
Confidence in controlling risk measures
Insurers increasingly use stochastic simulation approaches for estimating risk capital, but numerical errors are rarely measured. A control variate method can improve the accuracy dramatically without increasing the number of simulations.
Balancing the benefits and costs of GPUs
Speed is the key
Valuation of commodity-based swing options
Reseach Papers
Valid Assumptions Required: an analysis of VaR for energy markets
In this 10-part series, Brett Humphreys takes a fresh look at the widely used risk measure value-at-risk (VaR), urging risk managers to be more aware of the many assumptions that go into the calculation to produce the VaR number.
Fast correlation Greeks by adjoint algorithmic differentiation
Adjoint methods have recently been proposed as an efficient way to calculate risk through Monte Carlo simulation. Luca Capriotti and Mike Giles extend these ideas and show how adjoint algorithmic differentiation allows for fast calculation of price…
A rotationally invariant technique for rare event simulation
Because of their low probability, including extreme events in Monte Carlo calculations of the value-at-risk of a credit-risky portfolio requires many simulations. Here, Susanne Klöppel, Ranja Reda and Walter Schachermayer demonstrate a geometrically…
Calculation of variable annuity market sensitivities using a pathwise methodology
Under traditional finite difference methods, the calculation of variable annuity sensitivities can involve multiple Monte Carlo simulations, leading to high computational cost. A pathwise approach reduces this dramatically, while providing an unbiased…
Simulations with exact means and covariances
Attilio Meucci presents a simple method to generate scenarios from multivariate elliptical distributions with given sample means and covariances, and shows an application to the risk management of a book of options
Fast Monte Carlo Bermudan Greeks
In recent years, much effort has been devoted to improving the efficiency of the Libor market model. Matthias Leclerc, Qian Liang and Ingo Schneider extend the pioneering work of Giles & Glasserman (2006) and show how fast calculations of Monte Carlo…
Accelerated ensemble Monte Carlo simulation
Traditional vanilla methods of Monte Carlo simulation can be extremely time-consuming if accurate estimation of the loss distribution is required. Kevin Thompson and Alistair McLeod show that the ensemble Monte Carlo method, introduced here,…