Today, many industries are risky and banking is no exception to this list. However, competent and constant management of various risks contributes to profit. Nevertheless, it is worth taking into account that the risks in the banking sector are objective indicators and that these risks cannot be completely eliminated even with the use of advanced technologies and systems.

It is worth noting that in modern realities, with the ever increasing complexity of banking services and products, with the use of new data processing and storage systems, new different types of risk occur. Also, the entry of Kazakhstan banks into the international system of banks leads to the emergence of new types of risk. As an example, we can consider the emergence of new types of operational risk; they are directly related to equipping new equipment and various programs. Based on the foregoing, it can be concluded that in order to reduce risks in the banking sector and reduce its level to acceptable parameters, a systematic and universal improvement in the quality of management is necessary, as well as the introduction of modern automated systems for assessing these risks.

When analyzing the work of the banking sector, it was revealed that in practice second-tier banks systematically identify significant risks, and banks also analyze these risks. From the larger list of types of risk, it is worth highlighting the most significant of them, including credit risk, currency risk, market risk, liquidity risk, interest rate risk, as well as the risk of undermining the organization's business reputation. The analysis allows us to conclude that in our time the most significant type of risk is credit risk. Or the so-called risk of default on a loan that may arise in the interaction of the bank and the client.

This is due to the fact that in our time every second resident has a loan. Lending itself refers to the profitable activities of banks of any level, but at the same time, the issuance of loans is one of the risky banking operations. According to statistics, the level of creditworthiness decreases during global crises and with instability in the country. All this can adversely affect the banking sector, but also the country's economic system. Late repayment of loans, especially large loans can contribute to bank ruin. Sometimes large credit debts can lead to a systemic crisis of the banking system as a whole. All this can aggravate the unstable state of the banking system in the country as a whole. Based on this, it can be concluded that the proper management of credit risk is a major part of the development and prosperity of the banking sector.

When analyzing the risks that have arisen, one of the main indicators is to determine the level of risk. In order to determine this parameter, various methods for identifying and measuring the level of risks, as well as various analysis methods, have been created. Often these are all kinds of methods for determining a credit rating, which have their advantages and disadvantages. Today, there are various methods of analysis and assessment of the level of credit risk. These include: methods of fuzzy logic, the use of neural networks, decision tree, genetic algorithms, etc.

In this monograph for further research, an analysis of credit risk was adopted as one of the most important in the banking sector. When managing credit risks, it is necessary to determine the goals of the bank and also the means for their implementation within a certain time period. This strategy should consist of the main stages: determining the period of time (for example, short-term, medium-term and long-term planning); determination of the goals of managing the system of credit risks (for example, final and intermediate); development of credit risk management measures; development and improvement of a monitoring system for the implementation of strategic plans.

State programs to raise small and medium-sized businesses, as well as other state programs have an impact on the economic situation in the country. Today there is an increase in consumer lending. In turn, second-tier banks with the goal of successful work must carry out a qualitative and quick analysis of credit risk assessment. Also, with the development of the economy, the number of loans from entrepreneurs and legal entities is increasing. These prevailing conditions create additional problems for banks of both the first and second level. The burden on lending banking employees who are directly involved in risk analysis and risk assessment is increasing.

In this monograph, credit risk was chosen as the subject of research, this is due to the fact that the main part of the profit of the banking sector and microcredit organizations is the profit from loans and credits.

World experience shows that the use of modern automated systems is aimed at solving many banking problems. The use of automated systems improves the quality of analysis and helps reduce the time it takes to make a decision on a loan. The study of this thesis is aimed at eliminating the above problems by developing an automated risk analysis system.

A literature review made it possible to analyze the researchers who were directly involved in the analysis of various types of risk in the banking sector: Batrakova L. G., Belyaeva M. K., Belyakova A. V., Bukhtina M. A., Vorobyova L. I., Ivanova V. V., Ilyasova S. M., Kozlova A. A., Kosovana K. S., Li O. V., Maslenchenkova Yu. S., Nedosekina A. O., Pototsky E. G., Subbotina A., Suprunovich E. and many others scientists.

An analysis of the scientists who devoted their research to the application of the theory of fuzzy sets to build a model for assessing credit ratings made it possible to identify the specialists who made the most significant contribution. This list includes: Andreychikov A. V., Andreychikova O. N., Goldberg D., Zade L., Kovalev S. M., Kofman A., Kruglov V. V., Mamdani E., Melikhov A. N., Minaev Yu. N., Pilinsky M., Rutkovsky L., Sugeno M., Filimonova O. Yu., Holland J. and many others.

The aim of this work is to develop and study alternative approaches and methods of risk management, as well as tools based on them, for analyzing the credit risk of a commercial bank in consumer lending markets.

Based on the goal, the following tasks were set that determined the logic of the monograph research and its structure:

- it is necessary to analyze existing methods for determining the level of credit risk;

- it is necessary to justify the importance of a qualitative assessment of credit risk;

- it is necessary to determine the most important criteria for determining the credit rating of the borrower;

- it is necessary to develop an architectural model for assessing credit risk based on fuzzy logic;

- it is necessary to develop a model for assessing credit risk based on the Matlab program.

The object of the study are commercial banks, second-tier banks and microcredit organizations, providing the process of lending to legal entities and individuals.

The subject of the study is the process of analyzing bank credit risk using the fuzzy logic method.

The scientific novelty of the results obtained in the thesis is as follows:

- the monograph analyzes existing methods for determining the level of credit risk;

- substantiated the importance of a qualitative assessment of credit risk;

- the most important criteria for determining the credit rating of the borrower are determined;

- an architectural model was developed that is necessary for assessing credit risk based on fuzzy logic, which allows to improve its quality and reduce the time it takes to make a decision on a loan application;

- a credit risk assessment model based on the Matlab program was developed, which allows solving the problem of determining the level of credit rating, making intermediate and final conclusions, highlighting the strengths and weaknesses of the client, as well as making suggestions on the advisability of issuing a loan.

The theoretical and practical significance of the thesis consists in the possibility of using the proposed models and tools to optimize the process of analyzing credit risk by partially automating it. The credit risk analysis model presented in this paper allows us to effectively assess the level of credit risk. The ability to create your own assessment model on the basis of the developed automated assessment system provides banks with the opportunity to improve the quality of the issued conclusions about the reliability of the client, and therefore reduce the level of credit risk for the bank.