A Neural Stochastic Volatility Model

The volatility of the price movements reflects the ubiquitous In this paper, we take a fully data driven approach and determine uncertainty within financial markets. It is critical the configurations with as few exogenous input as that the level of risk (aka, the degree of variation), indicated possible, or even purely from the historical data. We propose by volatility, is taken into consideration before investment a neural network re-formulation of stochastic volatility decisions are made and portfolio are optimised (Hull by leveraging stochastic models and recurrent neural networks 2006); volatility is substantially a key variable in the pricing (RNNs). In inspired by the work from Chung et al. of derivative securities. Hence, estimating and forecasting (Chung et al. 2015) and Fraccaro et al. (Fraccaro et al. 2016), volatility is of great importance in branches of financial studies, the proposed model is rooted in variational inference and including investment, risk management, security valuation equipped with the latest advances of stochastic neural networks.