Elliott waves, Fibonacci analysis, neural networks, pattern recognition, prediction.

The article is focused on an analysis and pattern recognition in time series, which are fractal in nature. The proposal methodology is based on an interdisciplinary approach that combines artificial neural networks, analytic programming, Elliott wave theory and knowledge modelling. The heart of the methodology are a methods, which is able to recognize Elliott waves structures including their deformation in the charts and helps to more efficient prediction of its trend. The functionality of the proposed methodology was validated in experimental simulations, for whose implementation was designed and created an application environment. Experimental simulations have shown that the method is usable to a wider class of problems than the theory itself allows only Elliott waves.This paper introduces a methodology that allows analysis of Elliot wave?s patterns in time series for the purpose of a trend prediction.