iv Abstract This diploma thesis examines the impact of the COVID-19 crisis on the bank credit risk in the European Union. The analysis is performed using two sets of panel data. The first set contains data at the bank-level between 2012 and 2018 and is obtained from BankFocus batabase and the second set of data is obtained from the EBA Risk dashboard and contains data at the country-level between 2014 and 2020. Both datasets contain bank-specific variables and macroeconomic variables. We use the variables Cost of risk, Total capital ratio, Tier 1 ratio and NPE ratio as dependent variables. As representatives of the COVID-19 shock, we use the number of people infected with this disease, the number of deaths from this disease and the Stringency Index. We employ the GMM system for our analysis and test 5 hypotheses. We did not reject 3 hypotheses, namely that Cost of risk is a key determinant of credit risk and that the crisis caused by COVID-19 affects the variables Capitalo ratio and NPE ratio. We further concluded that the variables representing COVID-19 do not have a negative effect on credit risk, mainly due to the interventions of the ECB and the IASB. JEL Classification C12, C33, G01, G21 Keywords bank, COVID-19 crisis, credit risk management, Stringency index Title Author's e-mail Supervisor's e-mail...

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.

Under the Basel accords for measuring regulatory capital requirements, the set of credit risk parameters probability of default (PD), exposure at default (EAD) and loss given default (LGD) are measured with own estimates by the internal rating based approach. The estimated parameters are also the foundation of understanding the actual risk in a banks credit portfolio. The predictive performance of such models are therefore interesting to examine. The credit risk parameter LGD has been seen to give low performance for predictive models and LGD values are generally hard to estimate. The main purpose of this thesis is to analyse the predictive performance of a multi-gene genetic programming approach to symbolic regression compared to three benchmark regression models. The goal of multi-gene symbolic regression is to estimate the underlying relationship in the data through a linear combination of a set of generated mathematical expressions. The benchmark models are Logit Transformed Regression, Beta Regression and Regression Tree. All benchmark models are frequently used in the area. The data used to compare the models is a set of randomly selected, de-identified loans from the portfolios of underlying U.S. residential mortgage-backed securities retrieved from International Finance Research. The conclusion from implementing and comparing the models is that, the credit risk parameter LGD is continued difficult to estimated, the symbolic regression approach did not yield a better predictive ability than the benchmark models and it did not seem to find the underlying relationship in the data. The benchmark models are more user-friendly with easier implementation and they all requires less calculation complexity than symbolic regression.

Current regulation governing acquisition financing Abstract The thesis deals with financing of share deal acquisition operations. The first chapter points out idiosyncrasies of acquisition operations, providing context for the rest of the thesis. The second chapter deals with loan financing, one of the two financing methods described. The chapter starts off with Czech Civil Code's rules governing loans and goes on to provide an overview of stipulations used in corporate banking practice, including the usual arrangement of rights and obligations of lenders and borrower in case of syndicated loans. A subchapter about credit risk rounds off the second chapter. Not restricted to public law regulation, it describes derivatives used to hedge against credit risk and touches upon the influence of regulation on cost of loan financing. The third chapter is about bond financing. It offers a robust overview of Czech rules governing bonds as nominate debt securities and their issue. The consequent subchapter on placement of bonds handled by an investment firm serves as an equivalent of the banking practice- focused subchapter. Subjects that perform various tasks after placement in order to simplify the administration of a given issue are a topic which completes the third chapter. The conclusion of the thesis sets out...

Med en kvalitativ metod genom intervjuer har denna studie undersökt kreditgivares bedömningsprocess för kommersiella fastighetskrediter. Ett område av intresse att studera då det handlar om att bedöma risken att kreditgivaren inte återfår de pengar som lånats ut. Syftet har varit att undersöka processen i sin helhet, kassaflödet och värderingsflödet samt hur bådadera spelar in i bedömningen. Kassaflödet syftar på kredittagarens återbetalningsförmåga medan värderingsflödet syftar på värderingen av säkerheter.  Studiens empiri undersöker bedömningsprocessens olika delar med hänsyn till syftets fyra frågeställningar. Det framkommer att kredittagarens återbetalningsförmåga mäts genom ett detaljerat kassaflöde med relativt kort kalkylperiod. Värderingsflödet är ett mindre detaljerat kassaflöde med längre kalkylperiod för värdering av säkerheter. Studiens analys konstaterar att kassaflödet nästan uteslutande är det centrala i alla bedömningar och bland annat att nyckeltal kopplade till kassaflöde, som historiskt sett använts i bedömningen av rörelsedrivande bolag, kommit att användas även för kommersiella fastighetskrediter. Säkerheters marknadsvärden visar sig vara mindre betydelsefulla även under tider av ekonomisk kris då kovenanter kopplade till dessa ofta bryts men ändå accepteras, så länge återbetalningsförmågan kvarstår. Detta tycks vara naturligt då affärens välgång ligger i kassaflödens förmåga att försörja avtalsenlig ränta och amortering, inte i säkerheters värden. Ianspråktagande och likvidation av säkerheter leder i bästa fall enbart till återbetalning av utestående lånebalans. Ett fåtal fall då säkerheters värden får en större betydelse har dock under studien identifierats. / The study has, using a qualitative research method through interviews investigated creditors assessment procedure for commercial real estate mortgages. An area of interest to study since the purpose of credit risk assessment is about evaluating the risk of the creditor not getting back the money that’s been lent. The purpose has been to investigate the overall procedure and the assessment of cash flow for both repayment ability and valuation of collateral purposes and their roles in the credit risk assessment process. The study investigates the different parts of the procedure with regards to the four questions. It appears that the debtor’s repayment ability is measured through a detailed cash flow projected over a relatively short horizon. Valuation of property collateral is done using a less detailed cash flow projected over a longer horizon. The study concludes that the short-term cash flow almost exclusively is the central part in every assessment and among other findings that ratios referring to cash flow, that’s historically been used in the assessment of operating companies, are now being used for commercial real estate mortgages. The market value of collateral has proven to be less significant even during times of economic crisis when financial covenants referring to these are often broken, but still accepted, if the repayment ability withstands. This seems natural since the prosperity of the engagement lies within the ability of the cash flow to cover the loan servicing, not within the value of the collateral. A claim and liquidation of collateral in the best of cases only results in repayment of the outstanding loan balance. A few cases where the value of collateral receives a greater importance have however during the study been identified.

This thesis has explored the field of internally developed models for measuring the probability of default (PD) in credit risk. As regulators put restrictions on modelling practices and inhibit the advance of risk measurement, the fields of data science and machine learning are advancing. The tradeoff between stricter regulation on internally developed models and the advancement of data analytics was investigated by comparing model performance of the benchmark method Logistic Regression for estimating PD with the machine learning methods Decision Trees, Random Forest, Gradient Boosting and Artificial Neural Networks (ANN). The data was supplied by SEB and contained 45 variables and 24 635 samples. As the machine learning techniques become increasingly complex to favour enhanced performance, it is often at the expense of the interpretability of the model. An exploratory analysis was therefore made with the objective of measuring variable importance in the machine learning techniques. The findings from the exploratory analysis will be compared to the results from benchmark methods that exist for measuring variable importance. The results of this study shows that logistic regression outperformed the machine learning techniques based on the model performance measure AUC with a score of 0.906. The findings from the exploratory analysis did increase the interpretability of the machine learning techniques and were validated by the results from the benchmark methods. / Denna uppsats har undersökt internt utvecklade modeller för att estimera sannolikheten för utebliven betalning (PD) inom kreditrisk. Samtidigt som nya regelverk sätter restriktioner på metoder för modellering av kreditrisk och i viss mån hämmar utvecklingen av riskmätning, utvecklas samtidigt mer avancerade metoder inom maskinlärning för riskmätning. Således har avvägningen mellan strängare regelverk av internt utvecklade modeller och framsteg i dataanalys undersökts genom jämförelse av modellprestanda för referens metoden logistisk regression för uppskattning av PD med maskininlärningsteknikerna beslutsträd, Random Forest, Gradient Boosting och artificiella neurala nätverk (ANN). Dataunderlaget kommer från SEB och består utav 45 variabler och 24 635 observationer. När maskininlärningsteknikerna blir mer komplexa för att gynna förbättrad prestanda är det ofta på bekostnad av modellens tolkbarhet. En undersökande analys gjordes därför med målet att mäta förklarningsvariablers betydelse i maskininlärningsteknikerna. Resultaten från den undersökande analysen kommer att jämföras med resultat från etablerade metoder som mäter variabelsignifikans. Resultatet av studien visar att den logistiska regressionen presterade bättre än maskininlärningsteknikerna baserat på prestandamåttet AUC som mätte 0.906. Resultatet from den undersökande analysen för förklarningsvariablers betydelse ökade tolkbarheten för maskininlärningsteknikerna. Resultatet blev även validerat med utkomsten av de etablerade metoderna för att mäta variabelsignifikans.

Counterparty credit risk is present in trades offinancial obligations. This master thesis investigates the up and comingtechnology blockchain and how it could be used to mitigate counterparty creditrisk. The study intends to cover essentials of the mathematical model expectedloss, along with an introduction to the blockchain technology. After modellinga simple smart contract and using historical financial data, it was evidentthat there is a possible opportunity to reduce counterparty credit risk withthe use of blockchain. From the market study of this thesis, it is obvious thatthe current financial market needs more education about blockchain technology. / Motpartsrisk är närvarande i finansiella obligationer. Den här uppsatsen un- dersöker den lovande teknologin blockkedjan och hur den kan användas för att reducera motpartsrisk. Studien har för avsikt att täcka det essentiel- la i den matematiska modellen för förväntad förlust, samt en introduktion om blockkedjeteknologi. Efter att ha modellerat ett enkelt smart kontrakt, där historiska finansiella data använts, var det tydligt att det kan finnas en möjlighet att reducera motpartsrisk med hjälp av blockkedjan. Från mark- nadsundersökningen gjord i studien var det uppenbart att den nuvarande finansiella marknaden är i stort behov av mer utbildning om blockkedjan.

Магистерская диссертация посвящена вопросам управления портфельным кредитным риском коммерческих банков в условиях неопределенности и асимметрии информации. Целью исследования является разработка и экономическое обоснование методического инструментария, позволяющего оценивать и регулировать портфельный кредитный риск банка по корпоративным ссудам. Сделан вывод о том, что отраслевая диверсификация кредитов является инструментом, позволяющим снизить концентрацию кредитного риска по портфелю корпоративных кредитов. / Master thesis is devoted to the management of portfolio credit risk of commercial banks in conditions of uncertainty and information asymmetry. The aim of the study is the development and economic justification of methodological instruments to assess and manage portfolio credit risk of corporate loans. It is concluded that industrial diversification of loans is a instrument that allows to reduce concentration of credit risk of the corporate loan portfolios.

Магистерская диссертация посвящена вопросам оценки кредитного риска заемщиков – физических лиц. Целью исследования является разработка методического подхода по оценке кредитоспособности заемщиков как направления совершенствования управления кредитным риском. В работе сделан вывод о том, что повышение качества кредитного портфеля банка способствует повышению конкурентоспособности банка в условиях высокой конкуренции и нормативных требований Банка России. / Master thesis is devoted to the assessment of credit risk of individual borrowers. The aim of the study is the development a methodical approach to assess the creditworthiness of borrowers as a way to improve credit risk management. The work concluded that improving the quality of the credit portfolio of a bank contributes to improving competitiveness of bank in conditions of high competition and regulatory requirements of the Bank of Russia.

Payment service providers have unique credit portfolios with different characteristics than many other credit providers. It is therefore important to study if common credit risk estimation methods are applicable to their setting. By comparing simulation based methods for credit risk estimation it was found that combining Monte Carlo simulation with importance sampling and the asymptotic single risk factor model is the most suitable model amongst those analyzed. It allows for a combination of variance reduction, scenario analysis and correlation checks, which all are important for estimating credit risk in a payment service provider portfolio. / Betaltjänstleverantörer har unika kreditportföljer med andra egenskaper än många andra kreditgivare. Det är därför viktigt att undersöka om vanliga metoder för uppskattning av kreditrisk går att tillämpa på betaltjänstleverantörer. Genom att jämföra olika simulationsbaserade metoder för uppskattning av kreditrisk fann man att att kombinationen av Monte Carlo-simulering med Importance Sampling och en ASRF-modell är den mest lämpliga bland de analyserade metoderna. Det möjliggör en kombination av variansminskning, scenarioanalys och korrelationskontroller som alla är viktiga för att uppskatta kreditrisk i en betaltjänstleverantörsportfölj.