Neuro-Fuzzy Modeling Techniques in Economics

20

Authors: Marina Balzan

The paper considers the issue of improving the performance in enterprise activity analyzing the rating example results of the machine engineering enterprise. The improvement of the enterprise activity efficiency had been proven to be the result of enhancement in controlling over the quality of manufacturing process organization, achieved by applying the multi criteria analysis to the solution of the task of controlling over the enterprise performance quality. There had been substantiated the appropriateness of using the method of fuzzy multi criteria analysis as an alternative to the best variant in controlling over the performance quality. The above method enables to use the multi criteria analysis for choosing the best variant of the quality controlling project aimed at organizing the manufacturing process on the bases of pair wise comparison of the alternatives. Such an approach is suitable for the expert and is an advantage of the suggested method. The research resulted in the formulation of criteria for the evaluation of alternative variants: the degree of project preparation; expected effect; risks; quick development of the system for quality control; perspectives for the development of quality control system; project cost. One of the main characteristics of the suggested method is the application of the Zadeh-Bellman principle, following which the compensation for the drawbacks of some factors by the excess of the other is impossible. The solution is an alternative to be chosen, which simultaneously satisfies all the criteria for the most part. The specific example demonstrates the way the chosen set of criteria and the application of the developed approach forms the desired system for enterprise quality control with the expected efficiency.

27

Authors: Olena Zarutska

The financial analysis of banks and risk management systems’ effectiveness takes significant place in the system of banking supervision. To ensure an adequate remote control of bank activity it is necessary to use the set of instruments adapted to the structure and profile of risks at certain stages of system developing and separate structural and functional banks groups. The article is dedicated to the elaboration of the theoretical and methodological principles and practical tools of organization of the supervision in Ukraine in the transition conditions from micro to macroprudential bank supervision. The purpose of the article is developing approaches to the forming of medioprudential supervision system, picking out homogeneous structural and functional groups of banks as the objects for supervision, elaborated criterion basis for the picking up groups of banks, formalized their identifiable characteristics, suggested approaches to the early diagnostics of the banks financial stability loss threats, supervision activities differentiation according to the specification of the groups of banks. The subject of this study is toolkit reform of banking supervision in Ukraine using structural and functional analysis. Author proposed a differentiated approach to indi¬vidual structural and functional bank groups and dynamic modeling of banks financial condition with the help of Kohonen self-organizing map. Scientific novelty of this approach is to move from a technique grouping banks on the sizes of assets to grouping them in structural and functional characteristics. This allows you to direct the resources of banking supervision on high-risk areas. Financial indicators of a certain bank obtain a new qualitative assessment, taking into account his place in a variable system of banking system indicators.

31

Authors: Illia Sknar

The retrospective analysis of the evolution of concepts of constructing artificial neural networks in the context of the possibility of their further application to create artificial intelligence is carried out in the article. There are considered key achievements of international scientific community in this field starting from the first attempts of formalizing the neuron model and to the latest implementations of neural computing systems. The study concluded that there is the loss of researchers’ interest in constructing of an accurate model of the biological neuron and shifting attention to the creation of computer systems based on synaptic structures. The analysis also helped to identify the relationship between neurobiology achievements and qualitative leaps in field of construction of artificial neural networks, which shows the importance of further study of biological neural network structures and the need to create the most exact model of the biological neuron, as a key structural unit of the neural network. The conclusion is that there is an absence of a single unifying concept concerning the creation of biologically plausible artificial neural networks, so the author proposed the concept of the neuron structure decomposition into elementary biological functional subsystems. A feature of the proposed concept is the possibility of modeling of each neuron subsystem individually with further association of the components into an integrated system. Thus, the developed concept considers the possibility of adding and modifying elements of the neuron model for refinement and complication of its design in order to bring it to the maximum correspondence with the biological prototype. The practical value of the proposed concept lies in the possibility of developing a neural network structure on a fundamentally new level of quality with ensuring of the maximum similarity with the nervous system of a living organism.

44

Authors: Halyna Velykoivanenko, Liubov Trokoz

The article deals with the problem of overdue credit debt and establishing effective management of problem debts in the financial institutions. The essence and methodological features of the scoring assessment of borrowers of commercial banks, including collection scoring, are considered. The authors developed a mathematical model of collection scoring, based on a combination of tools of theories of fuzzy logic and artificial neural networks. The model has a hierarchical structure that takes into account the qualitative and quantitative variables which characterize the borrowers. The feature of the model is attracting of Kohonen self-organizing maps for setting the parameters of membership functions in the process of quantitative variables fuzzyfication, as well as for the automatic construction of a knowledge base at processing of qualitative variables. For aggregation of linguistic variables at each level of the hierarchy the authors used compositional integration rule, which allows generating fuzzy knowledge base without getting expert opi¬nions in terms of multi criterion and absence of comparison base for integral variables of top-level hierarchy. The practical value of the constructed model of collection scoring is the ability to develop recommendations for working with each segment of the portfolio of overdue loans in accordance with the calculated level of credit risk. Introduction to the work of financial institutions the credit risk assessment models on the basis of neuro-fuzzy techniques will have a positive impact on income from lending activities of commercial banks and contribute to the stability of the financial system as a whole.

14

Authors: V. Vitlinskiy, G. Melnyk

The linguistic approach to modeling of information risk management in corporate information system is proposed in this article. The fuzzy evaluation of quality of information risk management resources is grounded on the hierarchical model according to information security criteria. It’s developed the algorithm of defiion of generalized in- dicator of risk management resource quality in the article

16

Authors: S. Shtovba, O. Shtovba

The process of creation, promotion to market and exploitation of brands are tied with uncertainty of various natures that is caused by difficulty of predicting the reaction of a large people group. One of the most effective tools for modeling of humanistic systems under uncertainty is fuzzy techniques. It is established that most popular fuzzy techniques in branding are based on fuzzy inference, usage of fuzzy sets for uncertain information presenting, and fuzzy pairwise comparisons of alternatives. Bellman — Zadeh principle, fuzzy clus-tering and fuzzy queries to databases are rarely used in branding. The paper reviews the use of the mentioned fuzzy techniques for solving the practical problems of assessment, modeling, clustering and optimization, which aroused at different stages of the brand life cycle. Despite the advantages of fuzzy techniques for conditions of uncertainty of source information, in the practice of branding they are used in rare cases. Accordingly, the article focuses on the identification of perspective directions of implementation of fuzzy techniques into the brand management, and research of fuzzy modeling tools that can be applied to solve some applied problems with the formulation of recommendations for the design of models and related decision support systems.

26

Authors: O. Pritomanova, o Bilay

The authors have substantiated themethodological approach and have built a mathematicalmodel based on neuro-fuzzy technology for evaluation of problem loan.The proposed neuro- fuzzy model provides high adequacy for the relatively small sampling based on ex-pert linguistic assessments or which have inaccurate, incomplete or uncertain input data. The model based on neuro-fuzzy approach al-lows to create a decision support subsystem for managing problem credits to reduce the volume of bad debts in the loan portfolio.

28

Authors: T. Kichkina

The article is devoted to the improvement of insurance expertise at insurance of accidents in manufacturing using a mathematical modeling and information technologies in order to optimize the size of insurance rates, forecasting of number of victims of accidents and usage of preventive measures. There are developed the set of models, which are the basis for the insurance expertise and forecasting of number of accidents in manufacturing. The proposed set of models of insurance expertise allowed to make more accurate and informed decisions of insurance expert concerning accidents in manufacturing .

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.