Neuro-Fuzzy Modeling Techniques in Economics

4

Authors: Lotfi A. Zadeh

The past few decades have witnessed an accelerating growth in the use of mathematical concepts and techniques in the analysis of financial and economic systems. Such concepts and techniques have achieved notable successes. However, they fall short of providing realistic models for systems which function in an environment of pervasive imprecision and uncertainty. There is a reason. Traditional mathematical methods are based on classical, Aristotelian, bivalent logic. Bivalent logic is intolerant of imprecision and partiality of truth. What is widely unrecognized is that bivalent logic is intrinsically not the right logic for dealing with imprecision an uncertainty in financial and economic systems. What is needed for this purpose are methods based on soft computing—principally on fuzzy logic and neurocomputing. Basically, fuzzy logic is a system of reasoning of computation in which the objects of reasoning and computation are classes with unsharp (boundaries). In the realms of finance and economics, such classes are the norm rather than exception. Neuro-fuzzy methodology is a synergistic combination of concepts and techniques drawn from neurocomputing and fuzzy logic. Neurocomputing provides effective techniques for dealing with problems in which adaptation and identification of complex dependencies play important roles—as they do in many financial and economic systems. In recent years, many researchers in Eastern Europe, including Ukraine, have employed techniques drawn from fuzzy logic and neurocomputing. Launching of the journal "Neuro-Fuzzy Modeling Techniques in Economics" should make an important contribution to dissemination of knowledge and expertise in neuro-fuzzy-based methodologies not only in Eastern Europe and Ukraine but also worldwide. Furthermore, it will contribute to the establishment of closer contacts between Ukrainian researchers and scientific communities in other countries. I would like to congratulate the founders of "Neuro-Fuzzy Modeling Techniques in Economics" for taking an important step toward enhancing and enlarging the use of neuro-fuzzy-based methodologies in economics and finance—areas which play vital roles in modern society.

18

Authors: Yu. G. Lysenko, Y. Y. Bizyanov, A. G. Khmelyov

This article describes an approach to the design of budgets for the modern industrial enterprise with using artificial neural networks and fuzzy models. It’s proposed the structure of budgeting model and proposed a mathematical formulation of the problem. And also it’s grounded the usage of artificial neural networks for prediction and fuzzy mathematics for the calculation and evaluation of budgets.

19

Authors: K. D. Imanov, R. M. Akperov

It’s investigated in this paper the social system, which consists of such subsystems as economic, social, political, spiritual and natural environments. At the construction process of the fuzzy models of social system the information of various international organizations, Azerbaijan Republic and expert opinions were used. For assessment of social system quality indices were used the developed fuzzy models of separate subsystems. At solving tasks with usage of corresponding models it’s apply algorithm of the fuzzy weighted rules.

22

Authors: V. V. Vitlinskii

The concept of building a system of decision-making with usage of artificial intelligence tools is considered in the article. It’s revealed in the paper the principles of building the intelligent decision support systems, described the appropriate tools, emphasized the need to integrate risk into management decision-making systems.

28

Authors: A. A. Azarova, E. V. Antonuk

There are developed the methodological approach and constructed the appropriate structural and mathematical models of assessment the level of the strategic potential of enterprise in the article, which are based on mathematical tool of fuzzy logic and neural networks. The developed models allow not to consider all combinations of parameters at making decision, which significantly increases the speed of information processing, make it possible to consider its different nature, change the set of valuation parameters dynamically under conditions of variable internal and external environments. The peculiarities of complex target program of strategic potential using improvement constructing are presented. It allows identifying the main areas of funding and making efficient allocation of scarce resources.

32

Authors: G. I. Velykoivanenko, K. M. Mamonova

The article contains the results of research of alternative approaches to the modeling of companies’ investment attractiveness. In particular, the authors developed the system of mathematical and economic models, which allows to make investment decisions in conditions of incomplete and non-uniform information, based on the methodological tools of fuzzy logic theory and neural networks.