3.3.1 Comparative experimental investigations of efficiency of bankruptcy risk forecasting by systems CAMEL and FNN TSK

For bankruptcy risk forecasting in banking sphere of Ukraine, a special data set was collected consisting of 160 Ukrainian banks in the period 2012–2014 . It was divided into training and test subsamples in ratio 70/30 for FNN TSK, i.e., training samples consisted of 110 banks and test samples of 50 banks. The experiments were carried out, and the following results were obtained for FNN TSK (in average, 20 experiments were performed for each year and rules number), which are presented in Table 2. The data were collected in the year indicated in the first column, and the forecasting was made for next year, e.g., 2012-5—means bankruptcy risk forecasting in 2013 with use of 5 rules in FNN TSK by data of 2012. Two types of experiments were carried out with fixed parameters of membership functions (MF) and with training MF parameters. In Table 14, forecasting results for FNN TSK with adaptation of parameters are presented and in Table 15 with fixed parameters values.

In Table 16, forecasting results for FNN TSK with triangular MF are presented, while in Table 17 with trapezoidal MF.


#### Table 13.

Comparative results analysis of various forecasting methods.


The application of well-known matrix method by Nedosekin [11, 12] with level

% of errors

2012—0,7 14 28 8 6 2013—0,7 11 22 3 8 2014—0,7 16 32 9 7

(threshold) of cut 0.7 gave the following results presented in Table 18. Results obtained by rating system CAMEL are presented in Table 19

(threshold of 4).

Year and number of rules

Year and number of rules

Year and number of rules

Year and number of rules

Table 15.

Table 16.

Table 17.

Table 18.

95

General number of errors

DOI: http://dx.doi.org/10.5772/intechopen.82534

Forecasting results for FNN TSK with fixed parameters.

Forecasting results for FNN TSK with triangular MF.

Forecasting results for FNN TSK with trapezoidal MF.

Forecasting results of matrix method by Nedosekin.

General number of errors

General number of errors

General number of errors

% of errors

Banks Financial State Analysis and Bankruptcy Risk Forecasting with Application of Fuzzy…

% of errors

% of errors

—5 7 14 1 8 —5 8 16 1 6 —5 5 10 0 9 —10 9 18 4 7 —10 12 24 2 8 —10 11 22 4 9

—5 9 18 1 8 —5 7 14 1 6 —5 9 18 0 9 —10 11 22 4 7 —10 10 18 2 8 —10 13 26 4 9

—5 8 16 1 7 —5 8 16 0 8 —5 9 18 1 8 —10 9 18 3 6 —10 7 14 1 6 —10 11 22 4 7

Number of first type errors

Number of first type errors

Number of first type errors

Number of first type errors

Number of second type errors

Number of second type errors

Number of second type errors

Number of second type errors

#### Table 14.

Forecasting results for FNN TSK with FM parameters' adaptation.

Banks Financial State Analysis and Bankruptcy Risk Forecasting with Application of Fuzzy… DOI: http://dx.doi.org/10.5772/intechopen.82534


Table 15.

in proper time. In this case, bank's supervision system should give recommenda-

Accounting and Finance - New Perspectives on Banking, Financial Statements and Reporting

supervision and special urgent actions to prevent possible bankruptcy (see

Banks that got rating estimate 4 or 5 have serious problems, which demand strict

3.3.1 Comparative experimental investigations of efficiency of bankruptcy risk forecasting

For bankruptcy risk forecasting in banking sphere of Ukraine, a special data set was collected consisting of 160 Ukrainian banks in the period 2012–2014 . It was divided into training and test subsamples in ratio 70/30 for FNN TSK, i.e., training samples consisted of 110 banks and test samples of 50 banks. The experiments were carried out, and the following results were obtained for FNN TSK (in average, 20 experiments were performed for each year and rules number), which are presented in Table 2. The data were collected in the year indicated in the first column, and the forecasting was made for next year, e.g., 2012-5—means bankruptcy risk forecasting in 2013 with use of 5 rules in FNN TSK by data of 2012. Two types of experiments were carried out with fixed parameters of membership functions (MF) and with training MF parameters. In Table 14, forecasting results for FNN TSK with adaptation of parameters are presented and in Table 15 with fixed parameters values.

In Table 16, forecasting results for FNN TSK with triangular MF are presented,

"1" "2" "3" "4" "5"

Proper influence actions are performed over bank due to

Number of first type errors

demands of existing regulation laws of NBU.

Bank faces very serious problems, which may lead to bankruptcy.

Banks need urgent actions to prevent possible bankruptcy.

Number of second type errors

Bank has substantial drawbacks, which may lead to serious problems in future.

Bank supervision service should give clear instructions to overcome existing

problems.

% of errors

—5 6 12 0 6 —5 9 18 0 9 —5 8 16 1 7 —10 7 14 2 5 —10 5 10 0 5 —10 10 20 4 6

tions to managers how to overcome existing problems.

by systems CAMEL and FNN TSK

while in Table 17 with trapezoidal MF.

Bank financial state

Control from banks supervision service

Application of special actions

Year and number of rules

Table 13.

Table 14.

94

Bank integral rating

Bank is stable, reliable, and has skilled management

Comparative results analysis of various forecasting methods.

General number of errors

Forecasting results for FNN TSK with FM parameters' adaptation.

Table 13).

Forecasting results for FNN TSK with fixed parameters.


#### Table 16.

Forecasting results for FNN TSK with triangular MF.


Table 17.

Forecasting results for FNN TSK with trapezoidal MF.

The application of well-known matrix method by Nedosekin [11, 12] with level (threshold) of cut 0.7 gave the following results presented in Table 18.

Results obtained by rating system CAMEL are presented in Table 19 (threshold of 4).


Table 18.

Forecasting results of matrix method by Nedosekin.


ANFIS, fuzzy neural network TSK, Kromonov's method, Byelorussian bank associ-

Banks Financial State Analysis and Bankruptcy Risk Forecasting with Application of Fuzzy…

As the input data, the financial indices of Ukrainian banks were considered. While experiments with the adequate financial indicators were detected using

general liquidity coefficient (liquid assets + defended capital + capitals in reserve

FNN ANFIS. With increase of rules, number error probability first decreases,

2. The fuzzy GMDH gives better results using older data that is, more preferable

3. The comparison of FNN TSK with standard rating system CAMELS has shown that TSK enables to obtain more accurate bankruptcy risk forecasting.

4.In general, the comparative analysis had shown that fuzzy forecasting methods and techniques give better results than the conventional crisp and rating

4. Comparative analysis of bankruptcy risk forecasting methods for

banks bankruptcy risk forecasting, which may work under uncertainty with

Besides, the other goal of this investigation was to determine which factors (indicators) are to be used in forecasting models to obtain results close to real data. Therefore, we used a set of financial indicators (factors) of European banks according to the International accountant standard IFRS. The annual financial indicators of about 300 European banks were collected in 2004–2008, preceding the start of crisis of bank system in Europe in 2009. The data source is the information system Bloomberg [8]. The resulting sample included the reports only from the largest European banks as system Bloomberg contains the financial reports only from such banks. For correct utilization, input data were normalized in

methods for forecasting bankruptcy risk. But at the same time, the crisp methods are more simple in implementation and demand less time for their adjustment.

The results of successful application of fuzzy methods for bankruptcy risk forecasting of Ukrainian banks under uncertainty stimulated the further investigations of these methods application for financial state analysis of European leading banks. The main goal of this exploration was to investigate novel methods of European

1. It was established that FNN TSK gives much more accurate results than

ation method, rating system CAMELS, and matrix method (Nedosekin).

which the best forecasting results for Ukrainian banks were obtained:

general reliability factor (own capital/assets);

DOI: http://dx.doi.org/10.5772/intechopen.82534

instant liquidity factor (liquid assets/liabilities);

cross coefficient (total liabilities/working assets);

then attains minimum and then begins to raise.

for long-term forecasting (two or more years).

coefficient of profit fund capitalization.

European banks under uncertainty

4.1 Introduction

interval [0,1].

97

incomplete and unreliable data.

fund/total liabilities); and

Table 19.

Forecasting results of rating system CAMEL.

In Figure 2, the probability of error for different forecasting methods and various MF is presented.

In Figure 3, dependence of error probability versus number of rules in FNN TSK is presented.

Analyzing the performed experiments, the following conclusions may be made.

