Computationally intensive techniques for a fullyBayesian, decision theoretic approach to financialforecasting and portfolio selection

摘要

This paper considers the problem of modelling and forecasting for multivariate fi-rnnancial time series. The use of Dynamic Linear State Space models and StochasticrnVolatility models with Kalman filtering techniques to address this problem is consideredrnin the context of providing a modular software implementation. The combinationrnof these two approaches is presented with an illustrative example. We also show howrna marginal posterior forecast distribution may be used in order to implement a fullyrnBayesian decision theoretic approach to portfolio selection.