The Investigations of Fuzzy Group Method of Data Handling with Fuzzy Inputs in the Problem of Forecasting in the Financial Sphere. Yuriy Zaychenko

Abstract. The problem of forecasting models constructing using experimental data in terms of fuzziness, when input variables are not known exactly and determined as intervals of uncertainty is considered in this paper. The fuzzy group method of data handling is proposed to solve this problem. The theory of this method was suggested and researched in [1-3]. As it is well known, fuzzy GMDH allows to construct fuzzy models and has the following advantages:

1)The problem of optimal model finding is transformed to the problem of linear programming, which is always solvable;
2)There is interval regression model built as the result of method work out;
3)There is a possibility of adaptation of the obtained model;

The mathematical model of the problem mentioned above is built and fuzzy GMDH with fuzzy inputs is elaborated in the paper. The corresponding software kit, which uses the suggested algorithm, was developed. And also the experimental investigations and comparison of FGMDH with GMDH and neural nets in problems of stock prices forecasting was carried out and presented.

Keywords. GMDH, fuzzy model, error corridor, linear programming, approximation, models family.

References.
1. Zaychenko Yu. The Fuzzy Group Method of Data Handling and Its Application for Economical Processes Forecasting, Scientific Inquiry, - Vol. 7, No.1, June, 2006 - p.83-96.
2. Zaychenko Yu. Fuzzy method of inductive modeling in problems of macroeconomic indexes forecasting, System researches and informational technologies, no.3 of 2003, p. 25-45.
3. Zaychenko Yu. P., Zayetz I.O., O.V. Kamotsky, O.V. Pavlyuk. Research of different kinds of membership functions of fuzzy forecasting models parameters in fuzzy group method of data handling. USIM, 2003, no.2, p.56-67.