Applications of multivariate quasi-random sampling with neural networks
This work provides a method for more accurately modeling dependencies between financial stochastic processes, which is significant for quantitative analysts and risk managers.
This paper proposes using Generative Moment Matching Networks (GMMNs) to model cross-sectional dependence between stochastic processes, specifically geometric Brownian motions and ARMA-GARCH models. This approach is applied to pricing American basket call options and simulating predictive distributions, demonstrating benefits over parametric dependence models and achieving variance reduction by generating dependent quasi-random samples.
Generative moment matching networks (GMMNs) are suggested for modeling the cross-sectional dependence between stochastic processes. The stochastic processes considered are geometric Brownian motions and ARMA-GARCH models. Geometric Brownian motions lead to an application of pricing American basket call options under dependence and ARMA-GARCH models lead to an application of simulating predictive distributions. In both types of applications the benefit of using GMMNs in comparison to parametric dependence models is highlighted and the fact that GMMNs can produce dependent quasi-random samples with no additional effort is exploited to obtain variance reduction.