Neuro-Fuzzy Modeling Techniques in Economics

26

Authors: Nataliia Maksyshko, Victoriia Shapovalova

Real estate is considered as an important segment of the financial market in terms of the coherent market hypothesis, which combines the nonlinear deterministic model and statistical dynamic model and its basic assumption is that the dynamics of the market is divided into four phases: random walk, unstable transition, chaotic market and coherent market. Information base for research is statistical information market dynamics on the average price per square meter of real estate in the secondary real estate market, as well as derivative yields a time series of prices. In this article a method for identifying the phases of real estate market, based on the use of fuzzy model. The general scheme of the method consists of three parts: I — contains fuzzy model identification phase of the real estate market (due to the high level of uncertainty in the market price dynamics and its properties of nonlinearity, nonstationarity, etc.); II — verification of the model based on the comparison of the results of the identification data of peer reviews; III — is designed to train the model (optimizing of parameters of membership functions, based on which is carried out the classification). To build a model of the choice of input (explanatory) factors model, which involves the separation of the most informative features for the classification phase. For this goal, the properties of the dynamics of return rates in the phases of the coherent market requirements regarding quantitative indicators were analysed. As a result, quantitative characteristics of dynamics were selected, which were obtained by the use of complex statistical and fractal analysis and characterize the nature of the time series, estimate the depth of its memory, the local dynamics of resistance and the presence of landslides. The knowledge base model is built. The application of the constructed model will allow to implement a qualitative analysis of the current situation in the real estate market, to provide guidance on the selection of relevant instruments prediction.

31

Authors: Oleksandr Novoseletskyy, Olha Yakubets

The aim of the article is to develop effective economic and mathematical methods and models of assessment of legal entities creditworthiness, aimed at reducing of credit risk of borrowers of banking institutions. There are determined the conceptual aspects of modeling of legal entity creditworthiness on the basis of the system of financial ratios. The article proves that it is enough to use such financial ratios as instant and overall liquidity, ratio of accounts receivable and payable, return on sales, payable turnover, autonomy and solvency ratio in order to assess the creditworthiness of domestic enterprises. The synthesis of several approaches to the assessment of creditworthiness of a borrower, based on the use of methods of discriminant analysis, classification functions and neural networks of perceptron type, as well as on radial basis functions is developed in the article. For the purpose of assessment of creditworthiness the set of legal entities is divided into 4 classes: companies with high, satisfactory, low and unsatisfactory creditworthiness. If the creditworthiness is high it’s recommended to bank to grant loan, if it is satisfactory — to lend provided that the loan is secured by liquid collateral, if it is low or unsatisfactory — to deny loan. Testing of the developed models proved the effectiveness of the proposed approach. So, built in research the economic and mathematical models allow to improve essentially the accuracy of assessing the creditworthiness of potential borrowers and minimize credit risk of the banking institution.

37

Authors: Valentyna Oglih, Halyna Beschastna

This article contains the results of research in field of rating processes of insurance companies, in particular the analysis of existing policies and developing of an effective approach to the selection of insurance partners by commercial banks in order to improve profitability and financial reliability of banks on the basis of economic and mathematical modeling. Analysis of the results of the experiments provided an opportunity to detect in consistencies of traditional approaches to real conditions of functioning of banks and insurance companies. The suggested approach, which is based on the principles of neuro-fuzzy modeling and expert methods, combines scena¬rio calculations with considering qualitative and quantitative indicators, experts’ knowledge in the subject area. It allows to reach a topological ordering of objects, defining clusters and analysing the dynamics of development of insurers. Approbation of the models performed on data of insurers, which was working in Ukraine in 2008-2012. It helped to confirm the effectiveness of mathematical tools for getting adequate ratings of insurance companies.