The subject of this diploma thesis is managing credit risk in banks, as the most significant risk faced by banks. The aim of this work is to define the basic techniques, tools and methods that are used by banks to manage credit risk. The first part of this work focuses on defining these procedures and describes the entire process of credit risk management, from the definition of credit risk, describing credit strategy and policy, organizational structure, defining the most used credit risk mitigation tools to the regulatory requirements for credit risk management. The second part gives a more detailed view to credit risk measurement and evaluation and possibilities of credit risk hedging. Last part presents credit risk management in practise illustrated by the example of chosen bank.

Los bancos tienen como principal actividad para generar ingresos a la creación de créditos; sin embargo, debido a la incertidumbre que enfrentan al realizar sus operaciones, se ven expuestos al riesgo de crédito. Lo anterior crea un impacto negativo en el desempeño y rentabilidad bancaria; de ahí la importancia de la gestión de riesgo de crédito para garantizar la solidez financiera de los bancos. La presente investigación busca determinar cómo la gestión del riesgo de crédito afecta a la rentabilidad de los bancos peruanos, debido a que en los últimos años se muestra que los principales indicadores de gestión de riesgo de crédito se están deteriorando. La estimación se realiza a través de una base de datos longitudinal y la aplicación de la metodología Datos de Panel de Efectos Fijos teniendo como variable endógena a la rentabilidad y como exógena a dos indicadores de gestión de riesgo de crédito: El ratio de la cartera morosa y el ratio de adecuación de capital. Los resultados obtenidos indican que una inadecuada gestión de riesgo de crédito de los bancos peruanos afecta negativa su rentabilidad, pero no los llevan hasta el punto de quebrar o generar grietas en el sistema bancario. Por último, un banco con mayor tamaño incrementa su rentabilidad, ya que invierte en mejores herramientas para mejorar su gestión de riesgo de crédito. / Banks have as their main activity to generate income to the creation of credits; however, due to the uncertainty they face when carrying out their operations, they are exposed to credit risk. This creates a negative impact on bank performance and profitability; hence the importance of credit risk management to guarantee the financial soundness of banks. This research seeks to determine how credit risk management affects the profitability of Peruvian banks, since in recent years it has been shown that the main indicators of credit risk management are deteriorating. The estimation will be made through a longitudinal database and the application of the Fixed Effects Panel Data methodology, taking profitability as endogenous variable and two credit risk management indicators as exogenous: the delinquent portfolio ratio. and the capital adequacy ratio. The results obtained indicate that an inadequate credit risk management of Peruvian banks negatively affects their profitability but does not lead them to the point of going bankrupt or generating cracks in the banking system. Finally, a larger bank increases its profitability, as it invests in better tools to improve its credit risk management. / Trabajo de investigación

The financial stability of banks is crucial if they are to fulfil their role in facilitating transactions between borrowers and lenders. The purpose of this study was to investigate the effect of credit risk on the South African banking industry following a movement in credit ratings by rating agencies. Data from a sample of 11 banks were collected from 2006 to 2015. Econometric regression analysis was used to analyse the data. The results show that inflation, credit ratings, exchange rate, gross domestic product, unemployment rate, capital adequacy ratio and size of the bank are significant factors that determine "non-performing loans". Therefore, it is imperative that banks continuously monitor these factors and adapt their credit policies on "non-performing loans". This action would prepare banks for any adverse effects and ensure that the banking industry remains a sound and efficient contributor to the growth of the South African economy. / Business Management / M. Com. (Business Management)

In recent years the development and implementation of AI and machine learning models has increased dramatically. The availability of quality data paving the way for sophisticated AI models. Financial institutions uses many models in their daily operations. They are however, heavily regulated and need to follow the regulation that are set by central banks auditory standard and the financial supervisory authorities. One of these standards is the disclosure of expected credit losses in financial statements of banks, called IFRS 9. Banks must measure the expected credit shortfall in line with regulations set up by the EBA and FSA. In this master thesis, we are collaborating with a Swedish bank to evaluate different machine learning models to predict defaults of a unsecured credit portfolio. The default probability is a key variable in the expected credit loss equation. The goal is not only to develop a valid model to predict these defaults but to create and evaluate different models based on their performance and transparency. With regulatory challenges within AI the need to introduce transparency in models are part of the process. When banks use models there’s a requirement on transparency which refers to of how easily a model can be understood with its architecture, calculations, feature importance and logic’s behind the decision making process. We have compared the commonly used model logistic regression to three machine learning models, decision tree, random forest and XG boost. Where we want to show the performance and transparency differences of the machine learning models and the industry standard. We have introduced a transparency evaluation tool called transparency matrix to shed light on the different transparency requirements of machine learning models. The results show that all of the tree based machine learning models are a better choice of algorithm when estimating defaults compared to the traditional logistic regression. This is shown in the AUC score as well as the R2 metric. We also show that when models increase in complexity there is a performance-transparency trade off, the more complex our models gets the better it makes predictions. / Under de senaste ̊aren har utvecklingen och implementeringen av AI- och maskininl ̈arningsmodeller o ̈kat dramatiskt. Tillg ̊angen till kvalitetsdata banar va ̈gen fo ̈r sofistikerade AI-modeller. Finansiella institutioner anva ̈nder m ̊anga modeller i sin dagliga verksamhet. De a ̈r dock starkt reglerade och m ̊aste fo ̈lja de regler som faststa ̈lls av centralbankernas revisionsstandard och finansiella tillsynsmyndigheter. En av dessa standarder a ̈r offentligg ̈orandet av fo ̈rva ̈ntade kreditfo ̈rluster i bankernas finansiella rapporter, kallad IFRS 9. Banker m ̊aste ma ̈ta den fo ̈rva ̈ntade kreditfo ̈rlusten i linje med regler som faststa ̈lls av EBA och FSA. I denna uppsats samarbetar vi med en svensk bank fo ̈r att utva ̈rdera olika maskininl ̈arningsmodeller f ̈or att fo ̈rutsa ̈ga fallisemang i en blankokreditsportfo ̈lj. Sannolikheten fo ̈r fallismang ̈ar en viktig variabel i ekvationen fo ̈r fo ̈rva ̈ntade kreditfo ̈rluster. M ̊alet a ̈r inte bara att utveckla en bra modell fo ̈r att prediktera fallismang, utan ocks ̊a att skapa och utva ̈rdera olika modeller baserat p ̊a deras prestanda och transparens. Med de utmaningar som finns inom AI a ̈r behovet av att info ̈ra transparens i modeller en del av processen. Na ̈r banker anva ̈nder modeller finns det krav p ̊a transparens som ha ̈nvisar till hur enkelt en modell kan fo ̈rst ̊as med sin arkitektur, bera ̈kningar, variabel p ̊averkan och logik bakom beslutsprocessen. Vi har ja ̈mfo ̈rt den vanligt anva ̈nda modellen logistisk regression med tre maskininla ̈rningsmodeller: Decision trees, Random forest och XG Boost. Vi vill visa skillnaderna i prestanda och transparens mellan maskininl ̈arningsmodeller och branschstandarden. Vi har introducerat ett verktyg fo ̈r transparensutva ̈rdering som kallas transparensmatris fo ̈r att belysa de olika transparenskraven fo ̈r maskininla ̈rningsmodeller. Resultaten visar att alla tra ̈d-baserade maskininla ̈rningsmodeller a ̈r ett ba ̈ttre val av modell vid prediktion av fallisemang j ̈amfo ̈rt med den traditionella logistiska regressionen. Detta visas i AUC-score samt R2 va ̈rdet. Vi visar ocks ̊a att n ̈ar modeller blir mer komplexa uppst ̊ar en kompromiss mellan prestanda och transparens; ju mer komplexa v ̊ara modeller blir, desto ba ̈ttre blir deras prediktioner.

In this study we propose to enhance the predictive power of a Buy Now, Pay Later (BNPL) consumer credit scorecard by leveraging detailed product information. The object of analys is in this study is Klarna Bank AB, which is the largest retail finance provider in Sweden. This research conducts a quantitative study in order to firstly, investigate if it is possible to find subcategories that correlate more with credit risk than the existing product categories at Klarna. This will be investigated by categorizing already accepted orders into more granulated product categories than Klarna's existing level. Secondly, this study investigates how more detailed product categorization can improve a BNPL e-commerce consumer credit scorecard. Lastly, a qualitative analysis of what the business impact an implementation of this feature could entail for Klarna Bank AB is conducted. Our results demonstrate that it is possible to find subcategories that correlate more strongly with credit risk than the existing categories. The characteristics of the high-and low risk product categories align with existing research on online consumer behavior. More specifically, we found that luxury products, ego-related products, and products related to addictive behavior had the highest risk. We also contribute to existing research within the credit risk management field by finding that trending/new products on the market have a higher risk, and that the novelty of a product should be taken into consideration in credit risk prediction. By applying a hypothetical credit scoring model on a dataset of already accepted orders that took the new detailed product categories into consideration, the discrimination performance could be improved. However, risks regarding adding more data into a credit risk model need to be considered before implementing the proposed solution. Our study, therefore, demonstrates the potential of including more granulated product category information in a BNPL e-commerce consumer credit scorecard to improve risk prediction. While the results of this study are limited to the studied context, it is considered generalizable in that the proposed method could effectively be adapted to retrieve corresponding findings in other contexts. / Denna studie föreslår att förbättra prediktionsförmågan hos en konsumentkreditriskmodell inom Buy Now, Pay Later (BNPL) genom att utnyttja detaljerad produktinformation. Analysobjektet i studien är Klarna Bank AB, som är den största BNPL-aktören i Sverige. I detta arbete genomförs en kvantitativ studie för att först och främst undersöka om det är möjligt att hitta produktkategorier som korrelerar mer med kreditrisk än vad de nuvarande produktkategorierna på Klarna gör. Detta ska undersökas genom att kategorisera redan accepterade ordrar i mer granulerade produktkategorier än Klarnas befintliga nivå. Därefter ska det undersökas hur mer detaljerad produktkategorisering kan förbättra en kreditriskmodell för BNPL-företag. Till sist genomförs en kvalitativ analys över vilken affärspåverkan en implementering av denna lösning skulle kunna innebära för Klarna Bank AB. Våra resultat visar att det är möjligt att hitta underkategorier som korrelerar starkare med kreditrisk än de befintliga kategorierna hos Klarna. Egenskaperna hos de produktkategorier med hög och låg risk överensstämmer med befintlig forskning inom konsumentbeteenden online och psykologi. Mer specifikt fann vi att lyxprodukter, ego-relaterade produkter, och produkter relaterade till beroendebeteenden hade den högsta risken. Vi bidrar också till befintlig forskning inom forskningsfältet för kreditrisk genom att finna att trendiga/nya produkter på marknaden har högre risk och att det borde beaktas vid kreditriskbedömning. Genom att tillämpa en hypotetisk kreditvärderingsmodell på en dataset av redan accepterade ordrar, som tog hänsyn till de nya detaljerade produktkategorierna, kunde prediktionsförmågan förbättras. Risker med att lägga till mer data i en kreditriskmodell måste dock övervägas innan den föreslagna lösningen implementeras. Vår studie visar på potentialen i att inkludera mer detaljerad produktkategoriinformation i ett consumer credit scorecard för BNPL-företag för att på så sätt förbättra riskprediktionsförmågan. Även om resultaten av denna studie är begränsade till den studerade kontexten, anses det vara generaliserbart genom att den föreslagna metoden effektivt skulle kunna anpassas för att hitta motsvarande resultat i andra kontexter.

The potential of small and medium enterprises (SMEs) in promoting economic growth in both developed and developing countries is widely accepted and documented by both scholars and policy makers. Particularly lacking are studies on the evidence in support of the importance of credit rationing to the sustainability of SMEs in an emerging economy like South Africa’s. This specific problem, especially in the developing countries, has been identified as the major bottleneck in realising socio-economic potentials of SMEs in those countries. However, one of the major ways of addressing the challenge of inadequate funding that exists within the SME sector is the use of bank credit. This study was therefore undertaken to explore the role of commercial banks in the provision of credit to the SMEs in South Africa. This study focuses on the issue of the relationship between the banking industry and SMEs. In particular, the problem of credit rationing of, and discrimination against SMEs by commercial banks was investigated. Because credit rationing and finance gaps can stem from imperfections on either supply-side (banks), or demand-side (SMEs), or both, the intention of the study was to examine both of these variables in order to uncover the implications of their relationships. The empirical analysis is based on survey data collected by means of a structured questionnaire which was distributed amongst banks and SME borrowers in the Gauteng Province of South Africa. Contrary to the general view that commercial banks are disinclined to provide credit to SMEs, the study found that South African banks are keen to serve the SMEs and are therefore making efforts to penetrate this potentially profitable market segment. However, several obstacles are potentially restricting the involvement of banks with SMEs in South Africa. The findings revealed that regulations such as the Financial Intelligence Centre Act (FICA) and the National Credit Act (NCA) came out strongly as major hindrances of bank financing to SMEs. Furthermore, it was shown that compliance with the NCA was ranked higher than credit history and profitability as a factor hindering the approval of SME loans. - iii - However, by using the structural equation modelling (SEM), the results also show that there is a positive and significant influence of lending technology and collateral on the supply of credit to SMEs. Variables such as creditworthiness, collateral and e-banking were found to have a positive and significant impact on the provision of credit to SMEs by commercial banks. For both the supply- and demand-side analysis, technology came out as the most important predictor of SME access to finance. This means that banks should strive to align their lending techniques with the dynamic technological developments so as to reach as many SMEs as possible even in the geographically dispersed regions. It is anticipated that improving SME access to bank credit could be the key to the growth and sustainability of SMEs, the alleviation of poverty and unemployment; and consequently leading to the growth of the South African economy. / Business Management / D. Com. (Business Management)