This study aims to estimate the ratio of non-performing loans to total loans (NPL ratio), its determinants and its response to different macroeconomic shocks. As the last financial crises had negative impact on the economy of many countries of the world, we have to strive for preventive measures that would help us to fully or at least partly avoid future crises. It should be achieved by sound risk management practices of all financial institutions. Important part of these risk management practices shall be - among others - stress tests that would test the health of the institution under severe conditions and negative shocks. For this study the vector autoregression model (VAR methodology) is used to see the response of credit risk (in terms of NPL ratio) to macroeconomic shocks in the Czech Republic. The variables used for this study are quarterly time series data of the period from 2002 to 2011 (GDP, inflation rate, unemployment rate, koruna exchange rate (CZK/USD), and interest rate). For each of these variables the impulse response function was created, to show the impact of macroeconomic shocks and the speed of adjustment of NPL ratio to these shocks. Keywords: Financial Crises, Credit Risk Management, Non-performing loans, Macroeconomic Shocks, Czech Republic, VARs

Modelos de credit score são usualmente desenvolvidos somente com informações dos proponentes aceitos. Neste trabalho foram consideradas estratégias que podem ser utilizadas para o desenvolvimento de modelos de credit score com a inclusão das informações dos rejeitados. Foram avaliadas as seguintes técnicas de inferência de rejeitados: classificação dos rejeitados como clientes Maus, parcelamento, dados aumentados, uso de informações de mercado e ainda a estratégia de aceitar proponentes rejeitados para acompanhamento e desenvolvimento de novos modelos de risco de crédito. Para a avaliação e comparação dos modelos foram utilizadas as medidas de desempenho: estatística de Kolmogorov-Smirnov (KS), área sob a curva de Lorentz (ROC), área entre as curvas de distribuição acumulada dos escores (AEC), diferença entre as taxas de inadimplência nos intervalos do escore definidos pelos decis e coeficiente de Gini. Concluiu-se que dentre as quatro primeiras técnicas avaliadas, o uso de informaçõoes de mercado foi a que apresentou melhor desempenho. Quanto à estratégia de aceitar proponentes rejeitados, observou-se que há um ganho em relação ao modelo ajustado só com base nos proponentes aceitos. / Credit scoring models are usually built using only information of accepted applicants. This text considered strategies that can be used to develop credit score models with inclusion of the information of the rejects. We evaluated the techniques of reject inference: classification of rejected customers as bad, parceling, augmentation, use of market information and the strategy of accepting rejected proponents for monitoring and developing new models of credit risk. For the evaluation and comparison between models were used performance measures: Kolmogorov-Smirnov statistics (KS), the area under the Lorentz Curve (ROC), area between cumulative distribution curves of the scores (AEC), difference among the delinquency rate in the score buckets based on deciles (DTI) and the Gini coefficient. We concluded that among the first four techniques evaluated, the fourth (use of market information) had the best performance. For the strategy to accept rejected bidders, it was observed that there is a gain in relation to the model that uses only information of accepted applicants.

Métodos analíticos para concessão de crédito vêm apresentando enormes avanços nas últimas décadas, particularmente no que se refere a métodos estatísticos de classificação para identificar grupos de indivíduos com diferentes taxas de inadimplência. A maioria dos trabalhos existentes sugere decisões do tipo conceder o crédito ou não, considerando apenas de forma marginal o resultado esperado da operação. O presente trabalho tem o objetivo de propor um modelo de avaliação de risco de crédito mais complexo que os tradicionais modelos de Credit Scoring, que forneça uma perspectiva mais detalhada acerca do desempenho futuro de um contrato de crédito, e que vá além da classificação entre bom e mau pagador. Aliado a este ganho de informação na previsibilidade oferecida pelo modelo, também é objetivo ampliar o espaço de decisões do problema, saindo de uma resposta binária (como aceitar/rejeitar o crédito) para algo que responda à seguinte pergunta: qual é a taxa justa para cobrir determinado risco?. / Analytical methods for granting credit are presenting enormous advances in recent decades, particularly in the field of statistical methods of classification to identify groups of individuals with different rates of default. Most of the existing work suggests decisions of the type granting credit or not, regarding just marginally the expected outcome of the operation. This work aims to propose a model to evaluate credit risk with more complexity than the traditional \"Credit Scoring\" models, providing a more detailed view about the future performance of a credit agreement, which goes beyond the classification of good and bad payers. Coupled with this improvement of information offered by the model, it is also this works aim to expand the decision space of the problem, leaving a binary response (such as accept/reject the claim) to something that answers the following question: \"what is the fair rate to cover a given risk \".

Modelos de customer scoring são utilizados para mensurar o risco de crédito de clientes de instituições financeiras. Neste trabalho, são apresentadas três estratégias que podem ser utilizadas para o desenvolvimento desses modelos. São discutidas as vantagens de cada uma dessas estratégias, bem como os modelos e a teoria estatística associada a elas. Algumas medidas de performance usualmente utilizadas na comparação de modelos de risco de crédito são descritas. Modelos para cada uma das estratégias são ajustados utilizando-se dados reais obtidos de uma instituição financeira. A performance das estratégias para esse conjunto de dados é comparada a partir de medidas usualmente utilizadas na avaliação de modelos de risco de crédito. Uma simulação também é desenvolvida com o propósito de comparar o desempenho das estratégias em condições controladas. / Customer scoring models are used to measure the credit risk of financial institution´s customers. In this work, we present three strategies that can be used to develop these models. We discuss the advantages of each of the strategies, as well as the models and statistical theory related with them. We fit models for each of these strategies using real data of a financial institution. We compare the strategies´s performance through some measures that are usually used to validate credit risk models. We still develop a simulation to study the strategies under controlled conditions.

Modelos de Credit Scoring são utilizados para estimar a probabilidade de um cliente proponente ao crédito se tornar inadimplente, em determinado período, baseadas em suas informações pessoais e financeiras. Neste trabalho, a técnica proposta em Credit Scoring é Redes Bayesianas (RB) e seus resultados foram comparados aos da Regressão Logística. As RB avaliadas foram as Bayesian Network Classifiers, conhecidas como Classificadores Bayesianos, com seguintes tipos de estrutura: Naive Bayes, Tree Augmented Naive Bayes (TAN) e General Bayesian Network (GBN). As estruturas das RB foram obtidas por Aprendizado de Estrutura a partir de uma base de dados real. Os desempenhos dos modelos foram avaliados e comparados através das taxas de acerto obtidas da Matriz de Confusão, da estatística Kolmogorov-Smirnov e coeficiente Gini. As amostras de desenvolvimento e de validação foram obtidas por Cross-Validation com 10 partições. A análise dos modelos ajustados mostrou que as RB e a Regressão Logística apresentaram desempenho similar, em relação a estatística Kolmogorov- Smirnov e ao coeficiente Gini. O Classificador TAN foi escolhido como o melhor modelo, pois apresentou o melhor desempenho nas previsões dos clientes maus pagadores e permitiu uma análise dos efeitos de interação entre variáveis. / Credit Scoring Models are used to estimate the insolvency probability of a customer, in a period, based on their personal and financial information. In this text, the proposed model for Credit Scoring is Bayesian Networks (BN) and its results were compared to Logistic Regression. The BN evaluated were the Bayesian Networks Classifiers, with structures of type: Naive Bayes, Tree Augmented Naive Bayes (TAN) and General Bayesian Network (GBN). The RB structures were developed using a Structure Learning technique from a real database. The models performance were evaluated and compared through the hit rates observed in Confusion Matrix, Kolmogorov-Smirnov statistic and Gini coefficient. The development and validation samples were obtained using a Cross-Validation criteria with 10-fold. The analysis showed that the fitted BN models have the same performance as the Logistic Regression Models, evaluating the Kolmogorov-Smirnov statistic and Gini coefficient. The TAN Classifier was selected as the best BN model, because it performed better in prediction of bad customers and allowed an interaction effects analysis between variables.

Satellite Model Accuracy in Bank Stress Testing Abstract Filip Hamáček January 4, 2019 This thesis is dealing with credit risk satellite models in Czech Republic. Satellite model is a tool to predict financial variable from macroeconomic vari- ables and is useful for stress testing the resilience of the banking sector. The aim of this thesis is to test accuracy of prediction models for Probability of De- fault in three different segments of loans - Corporate, Housing and Consumer. Model currently used in Czech National Bank is fairly unchanged since 2012 and its predictions can be improved. This thesis tests accuracy of the original model from CNB by developing new models using modern techniques, mainly by model combination methods: Bayesian Model Averaging (currently used in European Central Bank) and Frequentist Model Averaging. Last approach used are Neural Networks. 1

[pt] Este trabalho visa analisar os modelos atuais de avaliação de risco de crédito aplicados a empresas não-financeiras e desenvolver um modelo estatístico com o emprego da ferramenta LOGIT - Regressão Logística com base nos clientes jurídicos de uma empresa do ramo industrial. Este modelo tem como objetivo principal determinar a probabilidade de um cliente ser considerado como adimplente ou inadimplente. Com esta ferramenta o analista de crédito pode definir até que ponto se torna interessante para a empresa efetuar uma venda a prazo para o cliente. / [en] This dissertation has the objective of analyzing the current models of credit risk in non financial companies and to develop a statistical model with Logistic Regression. The main purpose of this model is to determine the probability of a client (business company) being considered a good or bad risk. This model will allow the credit analyst to measure the credit risk involved with credit sales.

本研究主要著重信用風險對於可轉換公司債評價之影響。因可轉換公司債兼具股權與債權之特性，使得它在某些時候亦與一般債權一樣面臨公司無法完全清償的風險。本文的研究架構主要分為兩項：以公司資產價值及以普通股股價為可轉換公司債之標的資產，並將信用風險的設定融入模型之中。在實證部份，則以茂矽二與新纖二這兩檔可轉換公司債為樣本。當以公司價值做為標的時，可再區分為Merton模型的設定或是首次通過時間模型(First Passage Time Model)的設定，此二者並無明顯的差異，主要原因來自於可轉換公司債同時具有債券及股票的性質，公司提前破產與否對可轉換公司債的影響並不大。此外，當以公司普通股股價做為標的時，可再分為以信用價差(credit spread)與Jarrow and Turnbull (1995)來評價其價值，此時，需將不同的信用品質分離出來，給予不同的折現率，當股價處於深度價外時，可轉換公司債對信用風險的敏感度較高。若再以理論價值與市價做比較，則可發現無論是茂矽二或新纖二的理論價值皆高於市價，其中一部份來自於模型設定已將部份發行條款予以簡化所造成的誤差，更重要的原因乃是可轉換公司債的市場流動性不足，造成效率性低落所導致。

臺灣地區於民國９４年底發生的雙卡風暴（信用卡與現金卡），讓臺灣全體發卡銀行，於民國９５年度打銷信用卡及現金卡呆帳共新台幣1,629億元，造成發生當年本國銀行近新台幣74億元的虧損。這就是臺灣的銀行業一窩蜂轉向高獲利的消費金融業務時，完全忽略了信用風險管理。未建立並落實良好的信用風險管理機制，導致信用危機發生時，完全失控，讓銀行產生嚴重虧損。當年的雙卡風暴，令許多民營銀行的經營控制權讓手外資投資機構，或為其他銀行所併購。 　　本論文以信用卡發卡業務為例，探討信用風險管理之貸後管理(Portfolio Management)方法，協助銀行降低信用風險損失成本，提升獲利；透過對實務信用風險管理之精進，降低信用風暴產生時的衝擊。 　　透過本研究之個案證實，經營信用卡業務之金融機構，若能持有一套良善的信用風險貸後管理，當信用危機發生時，可以有效地控制信用風險損失的增加。以本研究為例，雙卡風暴發生時，全體本國銀行的年化信用風險損失率上升12.41%，但擁有良善信用風險管理的個案銀行的年化信用風險損失率僅增加9.04%，差異高達3.37%，再透過作業成本的降低，可使信用卡的淨資產報酬率相差達５％左右。因此，經營無擔保消費者貸款的金融機構，要維持競爭優勢，一定要了解並落實信用風險管理工作，尤其是貸後管理方面的作業，更是決定勝負之關鍵。 / A local credit crisis occurred in Taiwan from late 2005 to early 2007. During the crisis, the total credit losses of Credit Cards and Cash Card were NT$ 162.9 billion for all cards issuers in Taiwan for Year 2006. This big loss made the Taiwanese banks having a negative net-income at NT$7.4billion for Year 2006. The root cause was from ignoring the credit risk management while Taiwanese banks kept growing the consumer lending business. And finally a few local banks were sold to the foreign banks because they couldn’t take such big loss from the capital requirement. The primary objective of this thesis is to research the portfolio management on the credit card business to find out how to build a good portfolio management working model in terms of credit risk management to help the credit card issuers to reduce the credit losses and increase the net-income, and also minimize the impact when the credit crisis happens. It has been proven that the credit card issuer with an excellent portfolio management on credit risk can reduce the credit loss increase compared with the others when the credit crisis is coming. For instance, the overall Taiwanese bank’s average loss rate in 2006 increased by 12.41% over 2005 but the bank loss rate only increased by 9.04% during that local credit crisis. Considering the lower operating cost of the bank, the ROA difference will be around 5%. Therefore, if any bank would like to do the consumer lending business, they must understand what risk management methods they should have and really work on them, especially for the portfolio management, so that they can maintain a good position to compete with the others.

<p>Nedgångar i världsekonomin med påföljande likviditetsproblem hos företag har medfört negativa konsekvenser för banker, vilket skapade behov av effektiv kreditriskhantering. För att förhindra stora kreditförluster försöker banker ständigt minimera sina risker vid kreditgivning genom att identifiera fallgropar.</p><p>Syftet är att undersöka vilka faktorer som bidrar till kreditförluster och belysa hur Nordea kan minimera risker vid kreditgivning utifrån dessa faktorer.</p><p>Datainsamling skedde via granskning av litteratur och en fallstudie. Studieobjektet var affärsbanken Nordea där det genomfördes flera intervjuer med kreditansvariga på en regional nivå. För att ta reda på utvecklingen av kreditvolym inom Sverige sammanställdes data utifrån kreditgivningsstatistik från Nordea Hypotek AB.</p><p>Enligt teorin är kreditförluster beroende av direkta och indirekta faktorer. Medan de direkta faktorerna kan påverkas av en kreditanalytiker ligger de indirekta faktorer utanför dennes inflytande. Det kan konstateras att Nordea har lyckats minimera kreditrisker i avsevärd grad med reservation för vissa förbättringar och att de faktorer som förorsakar förluster har banken klarat av att hålla under kontroll.</p><p>Bankens grundläggande strategi i riskhanteringen är att använda sig av förnuftig kreditgivning. Samtliga respondenter har betonat vikten av att göra grundliga utredningar vid nya kreditansökningar samt frekventa uppföljningar vid en föraning på betalsvårigheter hos befintliga kredittagare. Genom dessa rutiner kan banken fånga upp problematiska affärstransaktioner och förebygga uppkomsten av kreditförluster.</p> / <p>Turbulence in the world economy with following liquidity problem in enterprises has lead to negative consequences for banks that creates a need for effective credit risk management. To prevent significant credit losses, banks tries constantly to minimize their risks in credit granting through identifying pitfalls.</p><p>The purpose is to investigate the factors that contribute to the credit losses and illustrate how Nordea can minimize risks in credit granting.</p><p>Data were gathered from the literature review and a case study. The object of study is the Swedish Business Bank Nordea where several credit managers has been interviewed at the regional level. To obtain a volume of credit development in Sweden, gathered the credit granting statistics of the source of Nordea Hypotek AB.</p><p>According to the theory credit losses are depending on direct and indirect factors. While direct factors can be affected by a credit analyst, indirect factors are outside of his influence. It can be stated that Nordea has been succeed in minimizing of risks at the considerable degree, with reservation for some improvements, and that some factors that cause losses the bank manage to keep under control.</p><p>Bank´s fundamental strategy in risk management is to use reasonable credit granting. All of respondents have stressed the importance of thorough inquiry on new credit application and frequent following up suspicions of payment difficulties with existing borrowers. Through these routines can bank capture problematic business transactions and prevent appearance of credit losses.</p>