[pt] Órgãos reguladores internacionais dos setores bancário e securitário têm incentivado a adoção de modelos internos, em apoio ao gerenciamento de riscos, para a determinação de capital mí­nimo regulatório. A maioria dos modelos pode ser decomposta em sub-modelos de determinação de capital para cada tipo de risco que a companhia está exposta. O capital requerido total será a agregação desses capitais individuais. Os riscos de uma companhia podem ter uma interdependância, em geral, não linear, impossibilitando a soma direta desses capitais. Um dos grandes desafios da modelagem é identificar, mensurar e incorporar essas dependências. A teoria de cópulas tem se mostrado uma ferramenta eficaz para agregação dos capitais uma vez que incorpora as estruturas de dependência dos riscos modelados na estimação do capital mínimo. Esta dissertação apresenta uma discussão geral sobre metodologias de mensuração de dependência entre riscos. Estes conceitos são utilizados, no final da dissertação, para a estimação do capital econômico de uma companhia de seguros. Como a cópula nos permite separar os efeitos das estruturas de dependência das caracterí­sticas peculiares às distribuições marginais, é possí­vel explorar o impacto das dependências dos riscos no capital requerido total. A sensibilidade do capital econômico diante do ajuste das cópulas é investigada. As medidas de risco utilizadas para determinar o capital foram o Value at Risk e o Condicional Value at Risk. / [en] Financial regulatory agencies have been encouraging the adoption, in risk management practices, of internal models in order to determinate the regulatory minimum capital. Most of the models can be decomposed in minor capital models, each associated to a particular risk source to which that the company is exposed. The regulatory capital will be the aggregation of these individual capitals. The companies´ risks may have non-linear dependencies which prevent the sum of the individual capitals. One of the greatest challenges of this modeling process is to identify, measure and incorporate the dependencies amongst the several risk sources. The relatively recent copula theory has been shown to offer an effective tool for the aggregation of capitals, by duly capturing and incorporating the dependence of the several risks sources when estimating the minimum capital. This dissertation presents a general discussion about a dependence measurement methodology between risks. This is then applied, at the end of dissertation, to the estimation of the economic capital of an insurance company. Since copulas allow us to separate the effects of the structure dependence to the peculiar characteristics of the marginal distribution, it is possible to explore the impact of dependencies of risks on the total economic capital. The sensitivities of the economic capital are investigated. The risks measures used to determinate the capital were the Value at Risk and Conditional Value at Risk.

金融市場的激烈震盪，往往會造成投資大眾與企業的重大損失，甚而危及企業的生存及整體金融市場的穩定與發展。而每當金融市場發生變化時首當其衝者常為金融證券相關產業。證券商所面臨之經營風險雖可區分為市場風險、信用風險、流動性風險、作業風險、法律風險及系統風險等六類，但以市場風險為最主要的風險來源，由近年來國內外多起金融機構的重大損失案例可為證。大型化，國際化及多元化為國內證券商之發展趨勢，由於業務多元化、大型化，將使證券商所持有之金融資產部位增加，業務複雜度、組織運作與管理難度增加，相對的經營風險亦提高。因此適當的風險管理機制，以維持良好的風險管理能力，與適當的資源配置是證券商在致力於追求業務擴展之餘，應加以特別注意的重要事項。 本研究主要在探討國內證券商所面對的經營風險有那些，以及其在風險管理上存在的問題與建議，並對主要的市場風險管理問題尋求解決方案及進行個案分析。風險控管的內涵主要包括：風險管理的組織運作、風險衡量之技術、風險管理之策略、風險管理政策與執行等。除探討一般風險管理之策略運用(風險分散、風險移轉、風險承擔及動態避險等的原理與方法)外，並就近年來頗受注目的，風險值風險衡量管理技術的運用與模型進行研究，包括一般所定義之風險值的說明與實務運用外，進一步討論個別模型（包括歷史模擬法、蒙地卡羅模擬法、變異數-共變異數法及波動度之衡量方式等）的計算方法、特點。而在證券商之現行風險管理政策方面，則著重於證券商風險控管之外部規範與內部制度及其所存在的問題。 而就國內證券商所面對的風險管理問題與對策，本文以為除了必須要注重人才的培育召募及落實管理制度的執行外，還必須要有一具效率的風險管理工具及符合風險管理需要的組織與運作模式。就『有效率的風險管理工具』的問題，由於財務工程的原理與資訊科技的技術，可以幫助企業在市場環境快速變化下，迅速掌握企業在經營各項業務與投資決策時所面臨的風險大小與風險承擔能力進而採取適當的避險策略以規避風險。本文建議以建構『風險值風險管理資訊系統』以為解決對策，而就『符合風險管理需要的組織與運作模式』的問題，本文則建議以建構『專業分工、權力制衡、風控獨立、風險績效衡量』的組織運作模式為解決方案。

在台灣即將加入WTO的前提下，各家券商、銀行等金融業者為了提升本身的競爭力不斷追求利潤最大化以及風險最小化為其首要目標，因此風險控管的重要性便與日遽增，風險管理的方法也不斷推陳出新，在眾多的方法中，如何尋求最適自身的方法，便是各家金融業者刻不容緩研究的課題，風險值（Value at Risk）便是近期發展出來的一種風險控管工具。 　本研究以台灣債券組合為例，建構短期與長期公債的投資組合進行評估，研究方法採用一階、二階常態法、偏態修正法、蒙第卡羅模擬法及歷史資料模擬法，並配合不同的信賴水準、移動視窗及不同的利率期間結構及標準差估計法，對債券投資組合進行比較分析與驗証。在風險值驗證方面，則採用回溯測試與前向測試兩種驗證方法加上統計學上的平均值與變異數兩種方法，分別對上述不同的模型方法作驗證。

The purpose with this study is to compare four different models to VaR in terms of accuracy, namely Historical Simulation (HS), Simple Moving Average (SMA), Exponentially Weighted Moving Average (EWMA) and Exponentially Weighted Historical Simulation (EWHS). These VaR models will be applied to one underlying asset which is the Brent Blend Oil using these confidence levels 95 %, 99 % and 99, 9 %. Concerning the return of the asset the models under two different assumptions namely student t-distribution and normal distribution will be studied

Banking and online financial services are part of our critical infrastructure. As such, they comprise an Achilles heel in society and need to be protected accordingly. The last ten years have seen a steady shift from traditional show-off hacking towards cybercrime with great economic consequences for society. The different threats against online services are getting worse, and risk management with respect to denial-of-service attacks, phishing, and banking Trojans is now part of the agenda of most financial institutions. This trend is overseen by responsible authorities who step up their minimum requirements for risk management of financial services and, among other things, require regular risk assessment of current and emerging threats.For the financial institution, this situation creates a need to understand all parts of the incident response process of the online services, including the technology, sub-processes, and the resources working with online fraud prevention. The effectiveness of each countermeasure has traditionally been measured for one technology at a time, for example, leaving the fraud prevention manager with separate values for the effectiveness of authentication, intrusion detection, and fraud prevention. In this thesis, we address two problems with this situation. Firstly, there is a need for a tool which is able to model current countermeasures in light of emerging threats. Secondly, the development process of fraud detection is hampered by the lack of accessible data.In the main part of this thesis, we highlight the importance of looking at the “big risk picture” of the incident response process, and not just focusing on one technology at a time. In the first article, we present a tool which makes it possible to measure the effectiveness of the incident response process. We call this an incident response tree (IRT). In the second article, we present additional scenarios relevant for risk management of online financial services using IRTs. Furthermore, we introduce a complementary model which is inspired by existing models used for measuring credit risks. This enables us to compare different online services, using two measures, which we call Expected Fraud and Conditional Fraud Value at Risk. Finally, in the third article, we create a simulation tool which enables us to use scenario-specific results together with models like return of security investment, to support decisions about future security investments.In the second part of the thesis, we develop a method for producing realistic-looking data for testing fraud detection. In the fourth article, we introduce multi-agent based simulations together with social network analysis to create data which can be used to fine-tune fraud prevention, and in the fifth article, we continue this effort by adding a platform for testing fraud detection. / Finansiella nättjänster är en del av vår kritiska infrastruktur. På så vis utgör de en akilleshäl i samhället och måste skyddas på erforderligt sätt. Under de senaste tio åren har det skett en förskjutning från traditionella dataintrång för att visa upp att man kan till en it-brottslighet med stora ekonomiska konsekvenser för samhället. De olika hoten mot nättjänster har blivit värre och riskhantering med avseende på överbelastningsattacker, nätfiske och banktrojaner är nu en del av dagordningen för finansiella institutioner. Denna trend övervakas av ansvariga myndigheter som efterhand ökar sina minimikrav för riskhantering och bland annat kräver regelbunden riskbedömning av befintliga och nya hot.För den finansiella institutionen skapar denna situation ett behov av att förstå alla delar av incidenthanteringsprocessen, inklusive dess teknik, delprocesser och de resurser som kan arbeta med bedrägeribekämpning. Traditionellt har varje motåtgärds effektivitet mätts, om möjligt, för en teknik i taget, vilket leder till att ansvariga för bedrägeribekämpning får separata värden för autentisering, intrångsdetektering och bedrägeridetektering.I denna avhandling har vi fokuserat på två problem med denna situation. För det första finns det ett behov av ett verktyg som kan modellera effektiviteten för institutionens samlade motåtgärder mot bakgrund av befintliga och nya hot. För det andra saknas det tillgång till data för forskning rörande bedrägeridetektering, vilket hämmar utvecklingen inom området.I huvuddelen av avhandlingen ligger tonvikten på att studera ”hela” incidenthanteringsprocessen istället för att fokusera på en teknik i taget. I den första artikeln presenterar vi ett verktyg som gör det möjligt att mäta effektiviteten i incidenthanteringsprocessen. Vi kallar detta verktyg för ”incident response tree” (IRT) eller ”incidenthanteringsträd”. I den andra artikeln presenterar vi ett flertal scenarier som är relevanta för riskhantering av finansiella nättjänster med hjälp av IRT. Vi utvecklar också en kompletterande modell som är inspirerad av befintliga modeller för att mäta kreditrisk. Med hjälp av scenarioberoende mått för ”förväntat bedrägeri” och ”value at risk”, har vi möjlighet att jämföra risker mellan olika nättjänster. Slutligen, i den tredje artikeln, skapar vi ett agentbaserat simuleringsverktyg som gör det möjligt att använda scenariospecifika resultat tillsammans med modeller som ”avkastning på säkerhetsinvesteringar” för att stödja beslut om framtida investeringar i motåtgärder.I den andra delen av avhandlingen utvecklar vi en metod för att generera syntetiskt data för test av bedrägeridetektering. I den fjärde artikeln presenterar vi ett agentbaserat simuleringsverktyg som med hjälp av bland annat ”sociala nätverksanalyser” kan användas för att generera syntetiskt data med realistiskt utseende. I den femte artikeln fortsätter vi detta arbete genom att lägga till en plattform för testning av bedrägeridetektering. / <p>QC 20151103</p>

Το ζητούμενο σε κάθε επιχείρηση είναι η αντιμετώπιση καταστάσεων οι οποίες μπορεί να παρουσιάσουν αυξημένη πιθανότητα απωλειών. Για να επιτευχθεί ο συγκεκριμένος στόχος είναι αναγκαίος ο εντοπισμός και ο καθορισμός της σημαντικότητας των επικείμενων κινδύνων. Αυτούς τους κινδύνους μπορούμε να τους κατατάξουμε σε επιχειρησιακούς, μη επιχειρησιακούς και χρηματοοικονομικούς. Η διαχείριση του κινδύνου δεν έχει ως πρώτο σκοπό την αποφυγή του κινδύνου, αλλά την ελαχιστοποίησή του, αφού πρώτα εντοπιστεί και καθοριστεί το πόσο σημαντικός είναι. Στόχος είναι να ποσοτικοποιηθεί ο κίνδυνος και να υπολογίζεται ένα μέτρο συνολικού κινδύνου, έτσι ώστε δίνοντας μια τιμή σε αυτόν, να αποφασίσουμε αν θα πάρουμε το ρίσκο να τον αναλάβουμε ή όχι, με μεγαλύτερη ευκολία. Ένα μέτρο συνολικού κινδύνου, προκύπτει από την προσέγγιση της δυνητικής ζημίας {VAR(Value−At−Risk)}. Η προσέγγιση αυτή αποτελεί μια ποσοστιαία κατανομή κέρδους και απώλειας σε ένα συγκεκριμένο χρονικό διάστημα. Μπορεί να χρησιμοποιηθεί από οποιοδήποτε οργανισμό εκτίθεται σε χρηματοοικονομικό κίνδυνο και συνοψίζει τη χειρότερη ζημία με δεδομένο διάστημα εμπιστοσύνης. Σκοπός της παρούσας εργασίας είναι η περιγραφή του τρόπου λειτουργίας της προσέγγισης της δυνητικής ζημίας (VAR). Για την αξιολόγηση του κινδύνου η δυνητική ζημία (VAR) χρησιμοποιεί τρεις μεθόδους προσομοίωσης, την Ιστορική, την Monte Carlo και την Variance−covariance προσομοίωση. Παρουσιάζονται οι μέθοδοι αυτοί, τα πλεονεκτήματα και τα μειονεκτήματά τους. Η εργασία καταλήγει σε μελέτη μιας εφαρμογής, με τη μέθοδο της Ιστορικής προσομοίωσης. / The aim of enterprises is to remedy situations, which may identify increased probability losses. In order to achieve this particular objective, it is necessary to determine the importance of imminent risks. These risks can be classified into operational, not operational and financial. The primary aim of Risk management is not to evade risk, but to minimize it. The risk must be located and we have to determine its importance. The objective is to quantify the risk and calculate one measure of total risk. One measure of total risk, is the Value at Risk (VAR) approach. In its most general form, the Value at Risk (VAR) measures the potential loss in value of a risky asset or portfolio, over a defined period for a given confidence interval. The aim of this essay is the description of Value at Risk (VAR) approach. For the evaluation of the risk the Value at Risk (VAR) approach uses three methods of simulation. The Historical, the Monte Carlo and the VarianceCovariance simulation. These three methods are presented along with their advantages and disadvantages. The essay is concluded with an application using the method of Historical simulation.

Στην παρούσα εργασία γίνεται μια ανασκόπηση της μεθόδου μέτρησης κινδύνου Value at Risk (VaR). Παρουσιάζουμε μερικούς βασικούς τρόπους μέτρησης του Value at Risk και εφαρμόζουμε σε δεδομένα ενός χαρτοφυλακίου συναλλαγματικών ισοτιμιών και στον γενικό δείκτη του χρηματιστηρίου Αθηνών διαφορετικά μοντέλα GARCH (IGARCH, TGARCH, EGARCH, GARCH) για την εκτίμηση του VaR με ορίζοντα μιας ημέρας (1- day ahead). Εφαρμόζουμε διαφορετικές υποθέσεις για την κατανομή των αποδόσεων (normal, student's-t, ged), χρησιμοποιούμε διαφορετικά μεγέθη δείγματος (250, 500, 750, 1000) και επίπεδα εμπιστοσύνης για το VaR (95% και 99%). Στην συνέχεια τα αποτελέσματα τού κάθε μοντέλου ελέγχονται με βάση τον έλεγχο του Kupiec για την καταλληλότητα τους. / In the present diplomatic essay we present a review of the method for risk measurement Value at Risk (VaR). We present a few basic ways of measuring Value at Risk and apply to data of an exchange rates portfolio and Athens stock exchange index different GARCH (IGARCH, TGARCH, EGARCH, GARCH) models for the estimation of the 1-day ahead VaR. We use various assumptions for the distribution of the returns (normal, student's-t, ged), various sample sizes (250, 500, 750, 1000) and VaR confidence levels (95% and 99%). Then the results of each model are tested using Kupiec test for their performance.

A mensuração do risco de um investimento é uma das mais importantes etapas para a tomada de decisão de um investidor. Em virtude disto, este trabalho comparou três métodos de estimação (tradicional, através da analise univariada dos retornos do portfólio; cópulas estáticas e cópulas dinâmicas) de duas medidas de risco: Value at Risk (VaR) e Expected Shortfall (ES). Tais medidas foram estimadas para o portfólio composto pelos índices BOVESPA e S&P500 no período de janeiro de 1998 a maio de 2012. Para as modelagens univariadas, incluindo as marginais das cópulas, foram comparados os modelos GARCH e EGARCH. Para cada modelo univariado, utilizamos as cópulas Normal, t-Student, Gumbel rotacionada e Joe-Clayton simetrizada, com isso totalizando 36 modelos comparados. Nas comparações do VaR e ES foram utilizados, respectivamente, o teste de Chritoffersen e o teste de Mcneil e Frey. Os principais resultados encontrados foram a superioridade de modelos que supõem erros com distribuição t-Student, assim como a identificação de mudança no comportamento dos parâmetros dinâmicos nos períodos de crise. / Measuring the risk of an investment is one of the most important steps in an investor's decision-making. With this in light, this study compared three estimation methods (traditional; by univariate analysis of portfolio returns; dynamic copulas and static copulas), of two risk measurements: Value at Risk (VaR) and Expected Shortfall (ES). Such estimated measures are performed for a portfolio composed by the BOVESPA and S&P500 indexes, ranging from January 1998 to May 2012. For univariate modelling (including copulas marginals), the GARCH and EGARCH models were compared,. Regarding copulas, we use Normal, t-Student, rotated Gumbel and symmetric Joe-Clayton, leading to a total of 36 models being compared. For the comparison of VaR and ES were used, respectively, the Christoffersen test, and the Mcneil and Frey test. The main results found were the superiority of models assuming the t-Student distributed errors, as well as the identification of a change in the behaviour of dynamic parameters in periods of crisis.

Dissertação (mestrado)—Universidade de Brasília, Instituto de Ciências Exatas, Departamento de Ciência da Computação, 2017. / Submitted by Gabriela Lima (gabrieladaduch@gmail.com) on 2017-12-05T12:41:14Z No. of bitstreams: 1 2017_IramAlvesdeSouza.pdf: 1901766 bytes, checksum: 4e8857aa24a5d2e0703cc7665a45b8b6 (MD5) / Approved for entry into archive by Raquel Viana (raquelviana@bce.unb.br) on 2018-01-30T15:47:19Z (GMT) No. of bitstreams: 1 2017_IramAlvesdeSouza.pdf: 1901766 bytes, checksum: 4e8857aa24a5d2e0703cc7665a45b8b6 (MD5) / Made available in DSpace on 2018-01-30T15:47:19Z (GMT). No. of bitstreams: 1 2017_IramAlvesdeSouza.pdf: 1901766 bytes, checksum: 4e8857aa24a5d2e0703cc7665a45b8b6 (MD5) Previous issue date: 2018-01-30 / A gestão de riscos e capital constituem-se em instrumentos fundamentais para a sustentabilidade do sistema bancário. Nesse sentido, o processo de mensuração e gestão dos riscos de mercado vem evoluindo rapidamente ao longo dos últimos anos, em especial, quanto aos tipos e características dos instrumentos financeiros negociados no mercado, como também no aumento da exigência de requerimento mínimo de capital para cobertura de perdas financeiras ou econômicas resultantes da flutuação nos valores de mercado de posições detidas pelas Instituições Financeiras. O presente trabalho é um estudo de caso, do tipo exploratório, descritivo e de carácter qualitativo e quantitativo. O objetivo principal é mensurar o Value at Risk - VaR diário de uma carteira de negociação (Trading Book), com base nas abordagens padronizada e modelos internos, considerando também no cômputo do VaR o uso do indicador de giro do volume de negócios (IGN) observado a partir da liquidez dos instrumentos financeiros registrados na carteira. A metodologia utilizada para cálculo do indicador IGN, levou em consideração os estudos publicados no artigo “Portfolio Turnover and Common Stock Holdings Periods”, e foi ajustado para capturar as características e a liquidez dos instrumentos financeiros negociados em mercado. O trabalho aborda em seu referencial teórico os principais métodos de mensuração do VaR, como também as dissemelhanças nas abordagens padronizada e modelos internos, identificando fatores relevantes que podem ser utilizados gerencialmente pela instituição para traçar políticas ou estratégias que reduzam ou controlem o nível de requerimento de capital de sua carteira de negociação exposta aos riscos de mercado. / Risk and capital management are fundamental instruments for the sustainability of the banking system. That way, the process of measuring and managing market risks has been evolving rapidly over the last few years, especially with regard to the types and characteristics of the financial instruments traded in the market, as well as on the increased needs of minimum capital requirements for hedging of financial or economic losses resulting from the fluctuation in the market values positions held by Financial Institutions. The present work is a case study, exploratory, descriptive and qualitative and quantitative features. The main objective is to measure the Value at Risk (VaR) of a trading book, based on the standardized approaches and internal models, also considering in the VaR calculation the use of the turnover indicator (IGN) observed from the liquidity of the financial instruments registered in the portfolio. The methodology used to calculate the IGN indicator took into account the studies published in the article "Portfolio Turnover and Common Stock Holdings Periods" and was adjusted to capture the characteristics and liquidity of the financial instruments traded in the market. The work addresses in its theoretical reference the main methods of measurement of VaR, as well as the dissimilarities in the standardized approaches and internal models, identifying relevant factors that can be used by the institution to manage policies or strategies that reduce or control the level of capital requirement of its trading portfolio exposed to market risks.

A mensuração do risco de um investimento é uma das mais importantes etapas para a tomada de decisão de um investidor. Em virtude disto, este trabalho comparou três métodos de estimação (tradicional, através da analise univariada dos retornos do portfólio; cópulas estáticas e cópulas dinâmicas) de duas medidas de risco: Value at Risk (VaR) e Expected Shortfall (ES). Tais medidas foram estimadas para o portfólio composto pelos índices BOVESPA e S&P500 no período de janeiro de 1998 a maio de 2012. Para as modelagens univariadas, incluindo as marginais das cópulas, foram comparados os modelos GARCH e EGARCH. Para cada modelo univariado, utilizamos as cópulas Normal, t-Student, Gumbel rotacionada e Joe-Clayton simetrizada, com isso totalizando 36 modelos comparados. Nas comparações do VaR e ES foram utilizados, respectivamente, o teste de Chritoffersen e o teste de Mcneil e Frey. Os principais resultados encontrados foram a superioridade de modelos que supõem erros com distribuição t-Student, assim como a identificação de mudança no comportamento dos parâmetros dinâmicos nos períodos de crise. / Measuring the risk of an investment is one of the most important steps in an investor's decision-making. With this in light, this study compared three estimation methods (traditional; by univariate analysis of portfolio returns; dynamic copulas and static copulas), of two risk measurements: Value at Risk (VaR) and Expected Shortfall (ES). Such estimated measures are performed for a portfolio composed by the BOVESPA and S&P500 indexes, ranging from January 1998 to May 2012. For univariate modelling (including copulas marginals), the GARCH and EGARCH models were compared,. Regarding copulas, we use Normal, t-Student, rotated Gumbel and symmetric Joe-Clayton, leading to a total of 36 models being compared. For the comparison of VaR and ES were used, respectively, the Christoffersen test, and the Mcneil and Frey test. The main results found were the superiority of models assuming the t-Student distributed errors, as well as the identification of a change in the behaviour of dynamic parameters in periods of crisis.