Multi indicator approach via mathematical inference for price dynamics in information fusion context

We focus on modelling price dynamics in financial markets via Theory of Complexity.We use soft computing techniques for describing price dynamics.Starting from Prospect Theory, we model a decision framework for financial trading.We show results on different financial instruments under varying assumptions. The modelling of financial market movements and the predictions of price are deeply linked to the complexity, non linearity and the dynamism of the market itself. Many hidden factors contribute to these two subjects, which refer to the different kinds of operators (as fundamentalist and behaviourist), the different objectives amongst the retails, the institutional and business operators, the different time ranges and the different allocation plans. Moreover, the news effects on shortest time range, the induced sentiment and market movers play a key role in the modelling of the financial market. Two decision variables, named Energy E and Entropy S are introduced. Some specific values of these two variables act as attractors in the state space E-S; conesequently these two variables are useful for describing the price dynamics during the different market status (i.e. up trend, down trend, accumulation, and distribution). The result is a new decision framework, where the investor, the trader and the analyst may perform their prospects and forecasts. A multiparametric methodology for financial trading, investment and prospects analysis is defined and introduced, by following the Prospect Theory and by assuming the price fluctuations as a dynamical process in the stochastic context.