Central Clearing Counterparties play a crucial role in financial markets, requiring robust risk management practices to ensure operational stability. A growing emphasis on risk analysis and stress testing from regulators has led to the need for sophisticated tools that can model extreme but plausible market scenarios. This thesis presents a method leveraging Wasserstein Generative Adversarial Networks with Gradient Penalty (WGAN-GP) to construct an independent scenario generator capable of modeling and generating return distributions for financial markets. The developed method utilizes two primary components: the WGAN-GP model and a novel scenario selection strategy. The WGAN-GP model approximates the multivariate return distribution of stocks, generating plausible return scenarios. The scenario selection strategy employs lower and upper bounds on Euclidean distance calculated from the return vector to identify, and select, extreme scenarios suitable for stress testing clearing members' portfolios. This approach enables the extraction of extreme yet plausible returns. This method was evaluated using 25 years of historical stock return data from the S&P 500. Results demonstrate that the WGAN-GP model effectively approximates the multivariate return distribution of several stocks, facilitating the generation of new plausible returns. However, the model requires extensive training to fully capture the tails of the distribution. The Euclidean distance-based scenario selection strategy shows promise in identifying extreme scenarios, with the generated scenarios demonstrating comparable portfolio impact to historical scenarios. These results suggest that the proposed method offers valuable tools for Central Clearing Counterparties to enhance their risk management. / Centrala motparter spelar en avgörande roll i dagens finansmarknad, vilket innebär att robusta riskhanteringsrutiner är nödvändiga för att säkerställa operativ stabilitet. Ökande regulatoriskt tryck för riskanalys och stresstestning från tillsynsmyndigheter har lett till behovet av avancerade verktyg som kan modellera extrema men troliga marknadsscenarier. I denna uppsats presenteras en metod som använder Wasserstein Generative Adversarial Networks med Gradient Penalty (WGAN-GP) för att skapa en oberoende scenariogenerator som kan modellera och generera avkastningsfördelningar för finansmarknader. Den framtagna metoden består av två huvudkomponenter: WGAN-GP-modellen och en scenariourvalstrategi. WGAN-GP-modellen approximerar den multivariata avkastningsfördelningen för aktier och genererar möjliga avkastningsscenarier. Urvalsstrategin för scenarier använder nedre och övre gränser för euklidiskt avstånd, beräknat från avkastningsvektorn, för att identifiera och välja extrema scenarier som kan användas för att stresstesta clearingmedlemmars portföljer. Denna strategi gör det möjligt att erhålla nya extrema men troliga avkastningar. Metoden utvärderas med 25 års historisk aktieavkastningsdata från S&P 500. Resultaten visar att WGAN-GP-modellen effektivt kan approximera den multivariata avkastningsfördelningen för flera aktier och därmed generera nya möjliga avkastningar. Modellen kan dock kräva en omfattande mängd träningscykler (epochs) för att fullt ut fånga fördelningens svansar. Scenariurvalet baserat på euklidiskt avstånd visade lovande resultat som ett urvalskriterium för extrema scenarier. De genererade scenarierna visar en jämförbar påverkan på portföljer i förhållande till de historiska scenarierna. Dessa resultat tyder på att den föreslagna metoden kan erbjuda värdefulla verktyg för centrala motparter att förbättra sin riskhantering.

This thesis aims to assist in the development of machine learning models tailored for stress testing. The main objective is to create models that can predict loan defaults while considering the impact of macroeconomic stress. By achieving this, Nordea can continue the development of machine learning models for stress testing by utilizing the models as a basis for further advancement. The research begins with an analysis of historical loan data, encompassing diverse customer and macroeconomic variables that influence loan default rates. Leveraging machine learning algorithms, feature selection methods, data imbalance management and model training techniques, a set of predictive models is constructed. These models aim to capture the intricate relationships between the identified variables and loan defaults, ensuring their suitability for stress testing purposes. The subsequent phase of the research focuses on subjecting the developed models to simulated adverse economic conditions during stress testing. By evaluating the models’ performance under various stressed scenarios, their ability to provide predictions is assessed. This stress testing process allows us to analyse the models’ capabilities of incorporating a stressed scenario in their predictions. The thesis concludes with an evaluation of the developed machine learning models and their abilities to identify defaulted loans in a stressed macroeconomy. By creating these models specifically tailored for stress testing loans, we will provide a basis for further development within the area of stress testing modeling. / Denna uppsats syftar till att bidra till utvecklingen av maskininlärningsmodeller lämpade för stress testing. Det främsta målet är att skapa modeller som kan förutsäga lån som kommer att misslyckas samtidigt som de beaktar påverkan av makroekonomisk stress. Genom att uppnå detta kan Nordea fortsätta utvecklingen av maskininlärningsmodeller för stress testning genom att använda modellerna som grund för ytterligare utveckling. Arbetet inleds med en analys av historisk lånedata, som omfattar olika kund- och makroekonomiska variabler som påverkar lån. Genom att använda oss av maskininlärningsalgoritmer, metoder för urval av förklarande variabler, hantering av dataobalans och tekniker för modellträning konstrueras en uppsättning prediktiva modeller. Dessa modeller syftar till att fånga de komplexa relationerna mellan de identifierade variablerna och låneavvikelser och säkerställa deras lämplighet för stress testning. Den efterföljande fasen av arbetet fokuserar på att utsätta de utvecklade modellerna för simulerade stressade ekonomiska förhållanden. Genom att utvärdera modellernas prestanda under olika stressade förhållanden bedöms deras förmåga att prediktera uteblivna lån. Denna process för stress testning gör det möjligt för oss att analysera modellernas förmåga att inkludera stressade förhållanden i sina prediktioner. Uppsatsen avslutas med en utvärdering av de utvecklade maskininlärningsmodellerna och deras förmåga att identifiera uteblivna lån i en stressad makroekonomi. Genom att skapa dessa modeller specifikt anpassade för stresstestning av lån kommer vi att ge en grund för ytterligare utveckling inom området.

This thesis deals with stress testing as a process that helps to assess the impact of potential adverse shocks on the soundness of a financial system. First section is dedicated to non-technical discussion about stress testing and to some methodological issues. The main focus lies on the system-wide macroeconomic stress testing. The empirical part of the thesis is a contribution to macroprudential analysis of the quality of the aggregate loan portfolio in the Czech Republic. This study adopts a vector autoregression model applied to the Czech banking sector in order to judge its stability and present some evidence on macroeconomic variables affecting the Czech banking system. As a measure of the strength of the loan portfolio is used the stock of non-performing loans vis-à-vis total loans in the sector. The thesis follows the widely used methodology and seeks to identify significant macroeconomic risk factors affecting the loan portfolio quality. The latter part aims also to forecast the most likely development of the loan portfolio.

In the present work we study the securitized products of ?financial markets with focus on collateralized debt obligations and the impact of fi?nancial crisis on the markets in the world. First part the thesis is focused on the methodology of the reasons behind launching these products, the portfolio, tranches and further on mechanisms how these structures are working. In the second part the thesis teoretically describes the valuation methods for which the Markov chains and copula functions are used. Further on follows the practical part with output from the quantitative analysis and at the end the thesis describes the impacts on economics of di?fferent countries and practically introduces the stress testing as the precaution tool.

The supervising institutions do not give to commercial banks indications what models have to be used for stress testing. This research was done in order to find out which mathematical/statistical models are and can be used in credit risk stress testing. Credit risk is one of the biggest financial risks that every bank faces. Stress testing is a tool of credit risk assessment that helps to estimate the consequences of the events that have really small probability to happen but if they occur, banks can have significant losses. This study determined that the most plausible event is adverse macroeconomic conditions. For this reason, models that include macroeconomic impact were presented. Vector autoregression and vector error correction model were tested using the empirical data received from Swedish central bank, Swedish statistics and Eurostat. For financial stability it is worth using vector autoregression or vector error correction model as they describe the macroeconomic environment in the most suitable way and they are appropriate for shock analysis by showing how the impact of any factor can change the whole system. Structure: introduction, main part (credit risk, methods and empirical analysis), publication, conclusions, references. Thesis consists of: 50 p. text without appendices, 13 pictures, 11 tables, 26 bibliographical entries. Appendices included. / Kredito įstaigų priežiūros institucijos nepateikia komerciniams bankams kokius metodus jie turėtų naudoti testavime nepalankiomis sąlygomis. Tiriamasis darbas buvo atliktas tuo tikslu, kad būtų išsiaiškinta kokie matematiniai ir statistiniai metodai yra ir gali būti naudojami kredito rizikos vertinime testuojant nepalankiomis sąlygomis. Kredito rizika yra viena iš didžiausių finansinių rizikų su kuria bankai susiduria. Testavimas nepalankiomis sąlygomis yra kredito rizikos vertinimo įrankis, padedantis nustatyti įvykių, kurių realizavimosi tikimybės yra mažos, tačiau jiems įvykus, bankai patirtų reikšmingus nuostolius, pasekmes. Šis tyrimas nustatė, jog labiausiai tikėtinas įvykis gali būti ypatingai nepalankios ekonominės sąlygos. Dėl šios priežasties darbe yra pristatyti metodai, kurie įvertina makroekonominių veiksnių įtaką. Vektorinė autoregresija ir vektorinis paklaidų korekcijos modelis buvo patikrinti naudojant Švedijos centrinio banko, Švedijos statistikos departamento ir Eurostat empirinius duomenis. Finansinio stabilumo įvertinimui vertėtų naudoti vektorinį autoregresijos ar vektorinį paklaidų korekcijos modelius, nes šie modeliai geriausiai aprašo ekonominę aplinką bei yra labai tinkami šokų analizei, kadangi įvertina bet kurio veiksnio įtaką visai sistemai. Struktūra: įvadas, pagrindinė dalis (kredito rizika, metodai ir empirinė analizė), publikacija, išvados, literatūros sąrašas. Tiriamasis darbas sudarytas iš: 50 psl. teksto be priedų, 13 paveikslų, 11... [toliau žr. visą tekstą]

Made available in DSpace on 2015-03-26T13:22:04Z (GMT). No. of bitstreams: 1 text completo.pdf: 757671 bytes, checksum: 435de7db4aaa7b1bdaf1bc5260f57dd9 (MD5) Previous issue date: 2014-03-11 / O objetivo do presente estudo foi investigar os efeitos do treinamento físico sobre as propriedades morfológicas e mecânicas de cardiomiócitos de camundongos knockout (KO) para receptores os β1- e β2 adrenérgicos. Camundongos C57BL/6J, KO para os receptores β1-adrenérgicos, FVB/N e KO para os receptores β2-adrenérgicos com 4 meses de idade, foram inicialmente separados aleatoriamente em 8 grupos: C57c, C57t, KO β1c, KO β1t, FVBc, FVBt, KO β2c e KO β2t. Os animais dos grupos treinados (C57t, KO β1t, FVBt, KO β2t) foram submetidos a um protocolo de treinamento aeróbico de 8 semanas, 5 dias por semana, 1hora por dia, com intensidade de 60% da velocidade máxima de corrida. 3 a 4 animais de cada grupo foram separados para a análise de contração celular com perfusão do agonista β-adrenérgico isoproterenol (ISO) [100nM]. Após a eutanásia, os cardiomiócitos do ventrículo esquerdo foram isolados por dispersão enzimática. O comprimento e a largura dos cardiomiócitos foram medidos utilizando um sistema de captação de imagens e o volume celular foi calculado. As contrações celulares foram medidas através da técnica de alteração do comprimento dos cardiomiócitos, após estimulação elétrica a 1 Hz, em temperatura controlada à 37oC, usando-se um sistema de detecção de bordas. Os resultados mostraram que os camundongos KO β1 apresentaram menor comprimento celular comparados aos C57. O grupo KO β2t apresentou maior comprimento celular comparado ao grupo KO β2c. O protocolo de treinamento aumentou a amplitude de contração, a velocidade máxima de contração e a velocidade máxima de relaxamento dos cardiomiócitos dos animais KO β1t e KO β2t. O ISO não alterou a amplitude de contração, a velocidade máxima de contração e de relaxamento nos cardiomiócitos dos camundongos KO β1+ISO, já os animais KO β2+ISO apresentaram aumento nas mesmas propriedades mecânicas. Conclui-se que o protocolo de treinamento aeróbico: a) aumentou as propriedades mecânicas dos cardiomiócitos dos animais KO β1 e KO β2; b) aumentou o comprimento dos cardiomiócitos dos camundongos KO β2; c) associado ao ISO não alterou as propriedades mecânicas nos cardiomiócitos dos camundongos KO β1 e reduziu nos cardiomiócitos dos camundongos KO β2. / The aim of this study was to investigate the effects of endurance training on cardiovascular parameters and morphological and mechanical properties of isolated cardiomyocytes from the left ventricle of β1-and β2 adrenergic receptors knockout mice. 4 months old C57BL/6J, β1- adrenergic receptor knockout (KO 1), FVB/N and β2-adrenergic receptor knockout (KO 2) mice were randomly allocated into one of the 8 groups: C57c, C57t, KO β1c, KO β1t, FVBc, FVBt, KO β2c e KO β2t. The animals of the trained groups (C57t, KO β1t, FVBt, KO β2t) underwent a protocol of aerobic training 8 weeks, 5 days/week, 1 hour/day, intensity of 60% of maximal speed. 3 to 4 animals in each group were divided for the analysis of cellular contraction with infusion of -adrenergic agonist isoproterenol (ISO) [100nM]. At sacrifice, the heart was removed and left ventricular myocytes were enzymatically dispersed. Cell length and width were measured using an image capture system and cell volume was calculated. Myocytes were stimulated at 1 Hz at controlled temperature (37oC) and cell contractility was measured by using an edge detection system. The results showed that KO 1 mice showed lower cell length compared to C57. The KO β2t group showed higher cell length compared to the KO β2c group. The training protocol increased the contraction amplitude, maximum contraction velocity and maximum relaxation velocity of cardiomyocytes of KO β1t and KO β2t animals. The ISO did not alter the amplitude of contraction, maximum contraction velocity and maximum relaxation velocity of cardiomyocytes from KO β1+ISO animals, while the KO β2+ISO animals showed an increase in the same mechanical properties. It is concluded that the aerobic training protocol: a) increased the mechanical properties of cardiomyocytes from KO β1t and KO β2t animals; b) increased the length of cardiomyocytes from β2 KO mice; c) associated with the ISO did not alter the mechanical properties of cardiomyocytes from β2 KO 1mice and reduced of cardiomyocytes from KO β2 mice.

Charles University in Prague Faculty of Social Sciences Institute of Economic Studies Credit Risk in the Macroprudential Framework: Three Essays DISSERTATION Author: PhDr. Jakub Seidler Supervisor: prof. Ing. Oldřich Dědek, CSc Academic Year: 2011/2012 Abstract This thesis focuses on proper credit risk identification with respect to macroprudential policies, which should mitigate systemic risk accumulation and contribute to higher financial stability of the financial sector. The first essay deals with a key credit risk parameter - Loss Given Default (LGD). We illustrate how the LGD can be estimated with the help of an adjusted Mertonian structural approach. We present a derivation of the formula for expected LGD and show its sensitivity analysis with respect to other company structural parameters. Finally, we estimate the five-year expected LGDs for companies listed on Prague Stock Exchange and find that the average LGD for the analyzed sample is around 20-50%. The second essay examines the issue of how to determine whether the observed level of private sector credit is excessive in the context of the "countercyclical capital buffer", a macroprudential tool proposed in the new regulatory framework of Basel III by the Basel Committee on Banking Supervision. An empirical analysis of selected Central and...

No description available.

Suite à la crise financière et économique de 2008, il a été constaté sur le portefeuille de négociation des banques un montant de capital réglementaire significativement inférieur aux pertes réelles. Pour comprendre les causes de cette insuffisance de capital réglementaire, il nous a paru important d'évaluer la fiabilité des modèles de mesure de risque de marché et de proposer des méthodologies de stress test pour la gestion des risques extrêmes. L'objectif est de mesurer le capital réglementaire sur un portefeuille de négociation composé d'actions et de matières premières par la mesure de la Value at Risk (VaR) et l'Expected Shortfall. Pour réaliser cet objectif, nous avons utilisé le modèle Generalized Pareto Distribution (GPD) et deux modèles internes utilisés par les banques : méthode de simulation historique et modèle de la loi normale. Une première évaluation de la fiabilité effectuée sur les trois modèles de risque sous l'hypothèse de volatilité constante, montre que les modèles internes des banques et le modèle GPD ne mesurent pas correctement le risque du portefeuille d'étude pendant les périodes de crise. Néanmoins, le modèle GPD est fiable en période de faible volatilité mais avec une forte surestimation du risque réel ; cela peut conduire les banques à bloquer plus de fonds propres réglementaires qu'il est nécessaire. Une seconde évaluation de la fiabilité des modèles de risque a été effectuée sous l'hypothèse du changement de la volatilité et par la prise en compte de l'effet asymétrique des rentabilités financières. Le modèle GPD s'est révélé le plus fiable quelles que soient les conditions des marchés. La prise en compte du changement de la volatilité a amélioré la performance des modèles internes des banques. L'intégration des scénarios historiques et hypothétiques dans les modèles de risque a permis d'évaluer le risque extrême tout en diminuant la subjectivité reprochée aux techniques de stress test. Le stress test réalisé avec les modèles internes des banques ne permet pas une mesure correcte du risque extrême. Le modèle GPD est mieux adapté pour le stress test. Nous avons développé un algorithme de stress test qui permettra aux banques d'évaluer le risque extrême de leurs portefeuilles et d'identifier les facteurs de risque responsables de ce risque. Le calcul du capital réglementaire sur la base de la somme de la VaR et du stress VaR n'est pas logique et entraîne un doublement des fonds propres réglementaires des banques. Le doublement de ces fonds propres aura pour conséquence le resserrement du crédit à l'économie. Nous observons que le coefficient multiplicateur et le principe de la racine carrée du temps de l'accord de Bâle conduisent les banques à faire un arbitrage en faveur des modèles de risque non fiables. / During the financial and economic crisis of 2008, it was noticed that the amount of capital required for banks' trading portfolio was significantly less than the real losses. To understand the causes of this low capital requirement, it seemed important to estimate the reliability of the market risk models and to propose stress testing methodologies for the management of extreme risks. The objective is to measure the capital requirement on a trading portfolio, composed of shares and commodities by the measure of the Value at Risk (VaR) and Expected Shortfall. To achieve this goal, we use the Generalized Pareto Distribution (GPD) and two internal models commonly used by banks: historical simulation method and model of the normal law. A first evaluation of the reliability made on the three risk models under the hypothesis of constant volatility, shows that the internal banks' models and the GPD model do not measure correctly the risk of the portfolio during the crisis periods. However, GPD model is reliable in periods of low volatility but with a strong overestimation of the real risk; it can lead banks to block more capital requirement than necessary. A second evaluation of the reliability of the risk models was made under the hypothesis of the change of the volatility and by considering the asymmetric effect of the financial returns. GPD model is the most reliable of all, irrespective of market conditions. The performance of the internal banks' risk models improves when considering the change of the volatility. The integration of the historic and hypothetical scenarios in the risk models, improves the estimation of the extreme risk, while decreasing the subjectivity blamed to the stress testing techniques. The stress testing realized with the internal models of banks does not allow a correct measure of the extreme risk. GPD model is better adapted for the stress testing techniques. We developed an algorithm of stress testing which allow banks to estimate the extreme risk of their portfolios and to identify the risk factors causing this risk. The calculation of the capital requirement based on the sum of the VaR and the stress VaR is not logical and leads to doubling the capital requirement of banks. Consequently, it conducts to a credit crunch in the economy. We observe that the multiplier coefficient and the principle of square root of time of the Basel's agreement lead banks to make arbitration in favor of risk models that are not reliable.

Context: Information technology is playing an important role in creating innovation in business. Due to increase in demand of information technology, web development has become an important field. PHP is an open source language, which is widely used in web development. PHP is used to develop dynamic web pages and it has the ability to connect with database. PHP has some good features i.e. cross platform compatibility, scalability, efficient execution and is an open source technology. These features make it a good choice for developers to choose PHP for web development. The maintenance of an application becomes difficult and performance being considerably reduced, if PHP is to be used without using its frameworks. To resolve these issues, different frameworks have been introduced by web development communities on the internet. These frameworks are based on Model, View, Controller design pattern. These frameworks provide, different common functionalities and classes in the form of helpers, components, and plug-in to reduce the development time. Due to these features like robustness, scalability, maintainability and performance, these frameworks are mostly used for web development in PHP, with performance being considered the most important factor. Objectives:The objective of this thesis is to compare and analyze the affect of data abstraction layer (ORM) on the performance of two PHP frameworks. These two frameworks are CakePHP and CodeIgniter. CAKEPHP has built-in support of object-relational mapping (ORM) but CodeIgniter has no built-in support of object-relational mapping (ORM). We considered load testing and stress testing to measure the performance of these two frameworks. Methods: We performed the experiment to show the performance of CakePHP (with ORM) and CodeIgniter (no ORM) frameworks. We developed two applications in both the PHP frameworks, with the same scope and design and measured the performance of these applications, with respect to load testing, with automated testing tool. The results have been obtained by testing the performance of both the applications on local and live servers. Conclusions:After analyzing the results we concluded that CodeIgniter is useful for small and medium sized applications. But CAKEPHP is good for large and enterprise level applications, as in stress conditions the CAKEPHP performed better than CodeIgniter on both local and live environment.