|
|
Mortgage lending and credit risk: Micro-level data analysis
Vachušková, Karolína ; Geršl, Adam (advisor) ; Jakubík, Petr (referee)
This thesis examines the effects of the debt service-to-income ratio (DSTI), debt-to-income ratio (DTI), and loan-to-value ratio (LTV) on credit risk. The dataset includes monthly loan-level data from around 250 thousand mortgages in the Czech Republic from July 2013 to July 2023. Using logit regressions, we confirm a positive effect of the level of DSTI, DTI and LTV on loan delinquency. Furthermore, we discover that the effects of these key lending variables are heterogeneous depending on the income and wealth classes as well as on the region of the client. Other explanatory variables align with general assumptions: a higher level of education, number of co-debtors, and GDP growth reduces the risk, whereas a higher interest rate increases the probability of delinquency. The thesis contributes to the debate on how effective macroprudential policy instruments using caps on DTI, DSTI and LTV are at employing a unique dataset. Keywords mortgage loans, credit risk, DSTI, LTV, microdata, Czech banking sector 1
|
|
|
Use of fuzzy logic for banking risk assessment
Maňková, Veronika ; Bobalová, Martina (referee) ; Janková, Zuzana (advisor)
The thesis focuses on the use of fuzzy logic in the banking sector for credit risk assessment. Artificial intelligence, especially the fuzzy logic method, is used to construct a model for evaluating whether a client poses a threat to the bank or not based on their creditworthiness. The determination of a client's creditworthiness involves the evaluation of both financial and non-financial indicators. The paper further describes the use of the MATLAB tool for the development and implementation of this model. The resulting model allows banks to better understand credit risk and enables them to make more informed lending decisions.
|
|
| |
|
| |
|
|
Credit Risk Measurement in Manufacturing Industry Companies in the Czech Republic
Karas, Michal ; Dohnal, Mirko (referee) ; Hrvolová, Božena (referee) ; Myšková, Renáta (referee) ; Režňáková, Mária (advisor)
The purpose of this doctoral thesis is to create a new bankruptcy prediction model and also to design how to use this model for the purposes of credit risk measuring. The starting-point of this work is the analysis of traditional bankruptcy models. It was found out that the traditional bankruptcy model are not enough effective in the current economic conditions and it is necessary to create a new ones. Based on the identified deficiencies of the traditional models a set of two new model series was created. The first series of the created models is based on the use of parametric methods, and the second one is based on the use of newer nonparametric approach. Moreover, a set of factors which are able to identify an imminent bankruptcy was analyzed. It was found, that significant signs of imminent bankruptcy can be identified even five years before the bankruptcy occurs. Based on these findings a new model was created. This model incorporates variables of static and even dynamic character for bankruptcy prediction purposes. The overall classification accuracy of this model is 92.27% of correctly classified active companies and 95.65% of correctly classified bankrupt companies.
|
|
|
An Impact of Financial Crisis on Finance of Company
Farkaš, Timotej ; Mackerle, Mojmír (referee) ; Rejnuš, Oldřich (advisor)
The bachelor thesis is concerning of an impact financial crisis on finance of company, especially on loaning. In teoretical part there are basic knowledge of loans and bank rates. Progress of bank rates and loans in Czech Republic is analysed in practical part. Result of the bachelor thesis is interpretation of an impact financial crisis on finance of company.
|
|
|
Rating Model for the Internal Assessment of the Creditworthiness of Customers
Vaňková, Leona ; Kotěrová, Monika (referee) ; Kocmanová, Alena (advisor)
The object of the following Diploma thesis was to design and test a simple and well-arranged credit tool – a Rating Model (further Model) which could be used as a preventative measure in credit policy. This rating model was designed in order to make the work of the Credit Risk Management sub-department and Rating Committee of KORADO more effective and at the same time to make more effective use of currently available internal and external data. Should the Company decide to use this Rating Model, a minimum of additional expenses would be incurred. The reader of this work will gain theoretical knowledge regarding financial analysis, credit management and fuzzy logic which is used in the calculation of a Total Rating. He/she will become acquainted with the major external agencies providing rating evaluations. As well, the reader may apprise the theoretical Rating model, including its practical use on four domestic and four overseas customers of KORADO. In conclusion there is an implementation of the Model, including a time schedule, an implementation team proposal as well as a budget of implementation and utilization costs.
|
|
|
Binning numerical variables in credit risk models
Mattanelli, Matyáš ; Baruník, Jozef (advisor) ; Teplý, Petr (referee)
This thesis investigates the effect of binning numerical variables on the per- formance of credit risk models. The differences are evaluated utilizing five publicly available data sets, six evaluation metrics, and a rigorous statistical test. The results suggest that the binning transformation has a positive and significant effect on the performance of logistic regression, feedforward artifi- cial neural network, and the Naïve Bayes classifier. The most affected aspect of model performance appears to be its ability to differentiate between eligible and ineligible customers. The obtained evidence is particularly pronounced for moderately-sized data sets. In addition, the findings are robust to the inclusion of missing values, the elimination of outliers, and the exclusion of categorical features. No significant positive effect of the binning transformation was found for the decision tree algorithm and the Random Forest model.
|
|
|
Energy Performance Certificate as One of Mortgage Default Determinants in the Czech Republic
Strašlipka, Jakub ; Pečená, Magda (advisor) ; Švéda, Josef (referee)
This thesis examines effects of buildings' energy efficiency, approximated by energy performance certificates, on default probabilities of mortgages in the Czech Republic. Data for the analysis is provided by a large Czech bank - cleaned sample contains information on 125 641 loans and is split into three groups based on collateral energy performance. Logit regression is employed for calculation of default probabilities and variations in conventional default predic- tors are controlled for. It is shown that mortgages on properties with certificate classes A, B have lower probabilities of default than those with certificate classes C, D by 7.1 bp (about 40%), ceteris paribus, whereas no statistical difference is found between default probabilities of mortgages on properties with classes C, D and those with classes E, F, G. The results can be considered by local banks in creation of climate risk management frameworks or in assessments of policies' impacts, or by other stakeholders in managing their expectations from banks. Due to partial use of the bank's internally estimated certificate proxies in the analysis and inconclusive results in a subsample of official certificates, follow-up research to confirm this thesis' findings is recommended.
|
|
|
Use of fuzzy logic for banking risk assessment
Maňková, Veronika ; Bobalová, Martina (referee) ; Janková, Zuzana (advisor)
The thesis focuses on the use of fuzzy logic in the banking sector for credit risk assessment. Artificial intelligence, especially the fuzzy logic method, is used to construct a model for evaluating whether a client poses a threat to the bank or not based on their creditworthiness. The determination of a client's creditworthiness involves the evaluation of both financial and non-financial indicators. The paper further describes the use of the MATLAB tool for the development and implementation of this model. The resulting model allows banks to better understand credit risk and enables them to make more informed lending decisions.
|
guest ::
