Machine Learning Techniques for Deciphering Implied Volatility Surface Data in a Hostile Environment: Scenario Based Particle Filter, Risk Factor Decomposition & Arbitrage Constraint Sampling

Abstract

The change subsequent to the sub-prime crisis pushed pressure on decreased financial products complexity, going from exotics to vanilla options but increase in pricing efficiency. We introduce in this paper a more efficient methodology for vanilla option pricing using a scenario based particle filter in a hostile data environment. In doing so we capitalise on the risk factor decomposition of the the Implied Volatility surface Parameterization (IVP) recently introduced in order to define our likelihood function and therefore our sampling methodology taking into consideration arbitrage constraints.