This thesis includes four essays on risk assessment with financial econometrics models. The first chapter provides Monte Carlo evidence on the efficiency gains obtained in GARCH-base estimations of VaR and ES by incorporating dependence information through copulas and subsequently using full maximum likelihood (FML) estimates. First, individual returns series are considered; in this case, the efficiency gain stems from exploiting the relationship with another returns series using a copula model. Second, portfolio returns series obtained as a linear combination of returns series related with a copula model, are considered; in this case, the efficiency gain stems from using FML estimates instead of two-stage maximum likelihood estimates. Our results show that, in these situations, using copula models and FML leads to a substantial reduction in the mean squared error of the VaR and ES estimates (around 50\% when there is a medium degree of dependence between returns) and a notable improvement in the performance of backtesting procedures. Then, chapter 2 analyzes the impact of the COVID-19 pandemic on the conditional variance of stock returns. In this work, we look at this effect from a global perspective, employing series of major stock market and sector indices. We use the Hansen’s Skewed-t distribution with EGARCH extended to control for sudden changes in volatility. We oversee the COVID-19 effect on the VaR. Our results show that there is a significant sudden shift up in the return distribution variance post the announcement of the pandemic, which must be explained properly to obtain reliable measures for financial risk management. In chapter 3, we assess VaR and ES estimates assuming different models for standardised returns such as Cornish-Fisher and Gram-Charlier polynomial expansions, and well-known parametric densities such as normal, skewed Student-t family of Zhu and Galbraith (2010), and Johnson. This paper aims to check whether models based on polynomial expansions outperform the parametric ones. We carry out the model performance comparison in two stages. First, a backtesting analysis for VaR and ES, and second, using the loss function approach. Our backtesting results in our empirical exercise suggest that all distributions, but the normal, perform quite well in VaR and ES estimations. Regarding the loss function analysis, we conclude that the Cornish-Fisher expansion usually outperforms the others in VaR estimation, but Johnson distribution is the one that provides the best ES estimates in most cases. Although the differences among all distributions (excluding the normal) are not great. Finally, chapter 4 assess whether accounting for asymmetry and tail-dependence in returns distributions may help to identify more profitable investment strategies in asset portfolios. Three copula models are used to parameterize the multivariate distribution of returns: Gaussian, C-Vine and R-Vine copulas. Using data from equities and ETFs from the US market, we find evidence that, for portfolios of 48 constituents or less, the R-Vine copula is able to produce more profitable portfolios with respect to both, the C-Vine and Gaussian copulas. However, for portfolios of 100 assets, performance of R- and C-Vine copulas is quite similar, being both better than the Gaussian copula.

Background: In today's society, there is more pressure to be sustainable and not least in the financial world. Several agreements, such as the Paris Agreement, have been created to steer countries towards more sustainability. When it comes to the economy, several SRI strategies have been developed to serve the same purpose. However, the problem that emerges is that investors who invest sustainably and use these strategies can lose returns and thus depart from their main goal of maximizing profits.   Purpose: The purpose of this paper is to examine how SRI strategies are used by investors when constructing their portfolios in terms of profit maximization. The paper will thus conclude if the underlying motivation behind the choice of strategy is affected by maximizing profit.   Method and implementation: By conducting a qualitative study and interviewing several fund managers at the largest banks and fund companies in Sweden, the authors aim to answer the research question. The answers provided by the respondents are presented and analyzed in the empirical section and linked to the study's theory.   Conclusion: In this study, there is clearly shown that by investing, according to SRI, a professional investor is still able to profit maximize. The authors, therefore, see that the new way of being rational as an investor is to include SRI strategies. The relationship with being both sustainable and profit-maximizing can be seen as a significant motivating factor. The same can be said about reduced ESG risk and creating legitimacy towards customers. Furthermore, a combination of strategies can be seen as a way to create an optimal portfolio by the investors. This further proves that sustainable investing is the most rational way of investing and a way to achieve an investors main goal to profit maximize.

In 2000 Campion High School, a Catholic, Jesuit, single-sex secondary school created and adopted the Grad-at-Grad statement as the school‘s expected school-wide learning results (ESLRs) and has articulated a need for a comprehensive, reliable assessment of these graduation outcomes. This case study used interviews, a survey, and participant observation to understand how the school has implemented and assessed the ESLRs since their inception. The study also thematically compared Jesuit educational philosophy to current theories of educative assessment and outcomes-centered curriculum development. Findings reveal that the school relies on a random, individual approach to curricular incorporation and has not incorporated the outcomes at the departmental level. Teachers at the school provide good role models for the Grad-at-Grad outcomes, and the Campus Ministry and Community Service programs provide meaningful learning experiences in relation to the outcomes. The school uses a variety of traditional assessment measures to assess students‘ growth toward the graduation outcomes. The study concluded that the school is in the middle of the implementation process and should utilize more professional development and the current theories of educative assessment and outcomes-centered curriculum design as it continues to implement and assess the ESLRs.

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.

Since the Basel Committee on Banking Supervision first suggested a transition to Expected Shortfall as the primary risk measure for financial institutions, the question on how to backtest it has been widely discussed. Still, there is a lack of studies that compare the different proposed backtesting methods. This thesis uses simulations and empirical data to evaluate the performance of non-parametric backtests under different circumstances. An important takeaway from the thesis is that the different backtests all use some kind of trade-off between measuring the number of Value at Risk exceedances and their magnitudes. The main finding of this thesis is a list, ranking the non-parametric backtests. This list can be used to choose backtesting method by cross-referencing to what is possible to implement given the estimation method that the financial institution uses. / Sedan Baselkommittén föreslog införandet av Expected Shortfall som primärt riskmått för finansiella institutioner, har det debatteras vilken backtesting metod som är bäst. Trots detta råder det brist på studier som utvärderar olika föreslagna backtest. I studien används simuleringar och historisk data för att utvärdera icke-parametriska backtests förmåga att under olika omständigheter upptäcka underskattad Expected Shortfall. En viktig iakttagelse är att alla de undersökta testen innebär ett avvägande i vilken utsträckning det skall detektera antalet och/eller storleken på Value at Risk överträdelserna. Studien resulterar i en prioriterad lista över vilka icke-parametriska backtest som är bäst. Denna lista kan sedan användas för att välja backtest utefter vad varje finansiell institution anser är möjligt givet dess estimeringsmetod.

In modern power systems, renewable energy has become an increasingly popular form of energy generation as a result of all the rules and regulations that are being implemented towards achieving clean energy worldwide. However, clean energy can have drawbacks in several forms. Wind energy, for example can introduce intermittency. In this thesis, we discuss a method to deal with this intermittency. In particular, by shedding some specific amount of load we can avoid a total system breakdown of the entire power plant. The load shedding method discussed in this thesis utilizes a Markov Decision Process with backward policy iteration. This is based on a probabilistic method that chooses the best load-shedding path that minimizes the expected total cost to ensure no power failure. We compare our results with two control policies, a load-balancing policy and a less-load shedding policy. It is shown that the proposed MDP policy outperforms the other control policies and achieves the minimum total expected cost.

Learning with neural networks depends on the particular parametrization of the functions represented by the network, that is, the assignment of parameters to functions. It also depends on the identity of the functions, which get assigned typical parameters at initialization, and, later, the parameters that arise during training. The choice of the activation function is a critical aspect of the network design that influences these function properties and requires investigation. This thesis focuses on analyzing the expected behavior of networks with maxout (multi-argument) activation functions. On top of enhancing the practical applicability of maxout networks, these findings add to the theoretical exploration of activation functions beyond the common choices. We believe this work can advance the study of activation functions and complicated neural network architectures. We begin by taking the number of activation regions as a complexity measure and showing that the practical complexity of deep networks with maxout activation functions is often far from the theoretical maximum. This analysis extends the previous results that were valid for deep neural networks with single-argument activation functions such as ReLU. Additionally, we demonstrate that a similar phenomenon occurs when considering the decision boundaries in classification tasks. We also show that the parameter space has a multitude of full-dimensional regions with widely different complexity and obtain nontrivial lower bounds on the expected complexity. Finally, we investigate different parameter initialization procedures and show that they can increase the speed of the gradient descent convergence in training. Further, continuing the investigation of the expected behavior, we study the gradients of a maxout network with respect to inputs and parameters and obtain bounds for the moments depending on the architecture and the parameter distribution. We observe that the distribution of the input-output Jacobian depends on the input, which complicates a stable parameter initialization. Based on the moments of the gradients, we formulate parameter initialization strategies that avoid vanishing and exploding gradients in wide networks. Experiments with deep fully-connected and convolutional networks show that this strategy improves SGD and Adam training of deep maxout networks. In addition, we obtain refined bounds on the expected number of linear regions, results on the expected curve length distortion, and results on the NTK. As the result of the research in this thesis, we develop multiple experiments and helpful components and make the code for them publicly available.

No description available.

No description available.

[pt] Neste trabalho apresentaremos a noção de valor esperado de uma variável aleatória, ou valor médio de uma quantidade aleatória, um conceito probabilístico extremamente importante e útil em diversas aplicações, mas que por razões históricas, não costuma ser ensinado no Ensino Médio. Além desse assunto, abordaremos também alguns problemas interessantes e desafiadores de Probabilidade, como por exemplo, questões dos vestibulares mais difíceis do País, como o do Instituto Militar de Engenharia (IME) e O Desafio em Matemática da PUC-Rio. Em várias das atividades propostas, ao longo nosso trabalho, iremos utilizar recursos computacionais como o Excel e o GeoGebra, e mostrar que podem ser fortes aliados ao ensino de Probabilidade e auxiliar no entendimento do conceito de Valor Esperado. / [en] In this dissertation we present the definition of the expected value of a random variable, an important probabilistic concept which is useful in many applications but which, for historical reasons, is not taught in high school in Brazil. We also discuss examples of interesting and challenging probability problems, including questions from some of the hardest exams in the country, such as the Vestibular for the Instituto Militar de Engenharia (IME) and the Desafio em Matemática of PUC-Rio. In many of the proposed activities, we use computational tools such as Excel and GeoGebra: these can become allies when teaching probability and help in the understanding of the concept of expected value.