The objective of this study is to discover the sources of securities return in forecasting stock return from different sides of potential factors including fundamental and market information. We test currency sensitivity, earnings variability, earnings yield, growth, leverage, trading activity, momentum, size, value, volatility, capital spending discipline, free cash flow, efficiency, solvency, earnings quality, corporate finance policy and technical 17 factors basing on different factor dimensions in this study. We construct a Taiwan multi-factor model by using the most significant factors for universal stocks according to 0HMSCI Barra¡¦s Multiple-Factor Modeling process, and then apply market neutral investment to build portfolios for performance back-testing. As a result, the most significant top five factors in forecasting are respectively ¡§Volatility2,¡¨ ¡§Earnings Quality1,¡¨ ¡§Trading1,¡¨ ¡§Volatility1¡¨ and ¡§Growth1¡¨ factors. In addition, we find the most useless bottom four factors in forecasting are respectively ¡§Size1,¡¨ ¡§Earning Yield1,¡¨ ¡§Value1,¡¨ and ¡§Capital Spending1.¡¨ No matter which strategies we adopt to build the portfolio, the Sharpe ratios of back-testing performance are all higher than the Benchmark, and all bring stable and consistent performance. It actually proves that this model is robust.

In this thesis we consider three different problems in the domain of portfolio optimisation. The first problem we consider is that of selecting an Absolute Return Portfolio (ARP). ARPs are usually seen as financial portfolios that aim to produce a good return regardless of how the underlying market performs, but our literature review shows that there is little agreement on what constitutes an ARP. We present a clear definition via a three-stage mixed-integer zero-one program for the problem of selecting an ARP. The second problem considered is that of designing a Market Neutral Portfolio (MNP). MNPs are generally defined as financial portfolios that (ideally)exhibit performance independent from that of an underlying market, but, once again, the existing literature is very fragmented. We consider the problem of constructing a MNP as a mixed-integer non-linear program (MINLP) which minimises the absolute value of the correlation between portfolio return and underlying benchmark return. The third problem is related to Exchange-Traded Funds (ETFs). ETFs are funds traded on the open market which typically have their performance tied to a benchmark index. They are composed of a basket of assets; most attempt to reproduce the returns of an index, but a growing number try to achieve a multiple of the benchmark return, such as two times or the negative of the return. We present a detailed performance study of the current ETF market and we find, among other conclusions, constant underperformance among ETFs that aim to do more than simply track an index. We present a MINLP for the problem of selecting the basket of assets that compose an ETF, which, to the best of our knowledge, is the first in the literature. For all three models we present extensive computational results for portfolios derived from universes defined by S&P international equity indices with up to 1200 stocks. We use CPLEX to solve the ARP problem and the software package Minotaur for both our MINLPs for MNP and an ETF.

本研究中，考慮連續時間下，附最低保證之長期最適投資策略；在利率模型中，為較能符合現實狀況，我們採用CIR模型；另外，在此策略中，我們將投資人之風險偏好加入模型中研究，最適化投資人到期時財富之效用函數，並用Cox & Huang之市場中立評價方法來解決數學模型問題。此篇研究顯示，最適之投資策略可以等價於某些共同基金之投資組合，這些共同基金能利用金融市場上之主要資產(market primary assets)來複製。 / In this study, we consider a portfolio selection problem for long-term investors. Dynamic investment strategy with the continuous-time framework incorporating the minimum guarantees are constructed. Maximizing expected utility of the terminal wealth is employed by investors to trade off profits in good future state against losses incurred in worse states. Follow the previous works of Deelstra et al. (2003), we concentrate on the simplest case of a one-factor Cox-Ingersoll-Ross (CIR) model in formulating the stochastic variation from the interest rate risks. Under the market completeness assumption, the fund growth is modelled under the market neutral valuation and the optimal rules are mapped into the static variational problem of Cox and Huang (1989). In this study, we show that the optimal portfolio is equivalent to a certain mutual fund that can be replicated by the market primary assets

Os modelos de otimização de carteiras baseados na análise média-variância apresentam dificuldades para estimação das matrizes de covariância, usadas no processo de otimização, o que leva a necessidade de métodos ad hoc para limitar ou suavizar as alocações eficientes recomendadas pelo modelo. Embora as carteiras obtidas por este método sejam eficientes, não é assegurado que o tracking error seja estacionário, podendo a carteira se distanciar do benchmark, exigindo frequentes recomposições. Neste artigo é empregada a metodologia de cointegração para otimização de carteiras no âmbito de duas estratégias: index tracking e estratégia long-short. A estabilidade das carteiras otimizadas através da cointegração em diferentes cenários de mercado, diminuindo custos relativos a frequentes recomposições da carteira, e níveis de retorno e volatilidade superiores aos benchmarks, mostram que a metodologia é uma ferramenta eficiente e capaz de gerar resultados robustos, se caracterizando como uma atraente ferramenta para a gestão quantitativa de recursos. Modelar a estrutura a termo da taxa de juros é extremamente importante para macroeconomistas e participantes do mercado financeiro em geral. Neste artigo é empregada a formulação de Diebold-Li para ajustar e fazer previsões da estrutura a termo da taxa de juros brasileira. São empregados dados diários referentes às taxas dos contratos de DI Futuro negociados na BM&F que apresentaram maior liquidez para o período de Janeiro de 2006 a Fevereiro de 2009. Diferentemente da maior parte da literatura sobre curva de juros para dados brasileiros, em que o modelo de Diebold- Li é estimado pelo método de dois passos, neste trabalho o modelo é colocado no formado de estado espaço, e os parâmetros são estimados simultaneamente, de forma eficiente, pelo Filtro de Kalman. Os resultados obtidos tanto para o ajuste, mas principalmente no que diz respeito à previsão, mostram que a estimação do modelo através do Filtro de Kalman é a mais adequada, gerando melhores previsões para todas as maturidades quando é considerado horizontes de previsão de um mês, três meses e seis meses. No terceiro artigo artigo nós propomos estimar o modelo dinâmico da estrutura a termo da curva de juros de Nelson e Siegel (1987) considerando duas especificações alternativas. Na primeira, nós consideramos os pesos dos fatores como variantes no tempo e tratamos a heterocedasticidade condicional via um modelo volatilidade estocática com fatores comuns. No segundo caso, consideramos um modelo onde os fatores latentes seguem individualmente processos autoregressivos com volatilidade estocástica. Os assim chamados fatores de volatilidade buscam capturar a incerteza ao longo do tempo associada ao nível, inclinação e curvatura da curva de juros. A estimação é realizada através de métodos de inferência bayesiana, por Markov Chain Monte Carlo. Os resultados mostram que os fatores de volatilidade são altamente persistentes, dando suporte ao fato estilizado de que os choques na volatilidade das taxas de juros são altamente persistentes, e também indicam que o uso de estruturas de volatilidade estocástica levam a melhores ajustes dentro da amostra para a curva de juros observada. / The traditional models to optimize portfolios based on mean-variance analysis aim to determine the portfolio weights that minimize the variance for a certain return level. The covariance matrices used to optimize are difficult to estimate and ad hoc methods often need to be applied to limit or smooth the mean-variance efficient allocations recommended by the model. Although the method is efficient, the tracking error isn’t certainly stationary, so the portfolio can get distant from the benchmark, requiring frequent re-balancements. We used the cointegration methodology to devise two quantitative strategies: index tracking and long-short market neutral. We aim to design optimal portfolios acquiring the asset prices’ co-movements. We used Ibovespa’s index and stocks from Jan-2000 to Dec-2008. The results show that the devise of index tracking portfolios using cointegration generates goods results, replicating the benchmark’s return and volatility. The long-short strategy generated stable returns under several market circumstances, presenting low volatility. Modeling the term structure of interest rate is very important to macroeconomists and financial market practitioners in general. In this paper, we used the Diebold-Li interpretation to the Nelson Siegel model in order to fit and forecast the Brazilian yield curve. The data consisted of daily observations of the most liquid future ID yields traded in the BM&F from January 2006 to February 2009. Differently from the literature on the Brazilian yield curve, where the Diebold-Li model is estimated through the two-step method, the model herein is put in the state-space form, and the parameters are simultaneously and efficiently estimated using the Kalman filter. The results obtained for the fit and for the forecast showed that the Kalman filter is the most suitable method for the estimation of the model, generating better forecast for all maturities when we consider the forecasting horizons of one and three months. In the third essay we propose to estimate the dynamic Nelson-Siegel model of yield curve considering two alternative specifications. At first, we consider the factor loadings such as time-varying conditonal heteroskedasticity and treat via a common factors of stochastic volatility models. In the second case, we consider a model where the latent factors individually following autorregressive process with stochastic volatility. The volatility factors seek to capture the uncertainty over time associated with level, slope and curvature of yield curve.The estimation is performed through bayesian inference, Markov Chain Monte Carlo. The volatility factors showed high persistence, supporting the stylized fact that shocks in the volatility of interest rate are highly persistent, and also indicate that the used of structures of stochastic volatility lead to better in-sample fits of the observed yield curve.

This Thesis attempts to construct a Taiwan equity multi-factor model using fundamental cross-sectional approach step by step. It is found that the model involves 28 explanatory factors (including 20 industry factors) and its explanatory power is 58.6% on average. The results of the estimations can be considered very satisfactory. Moreover, based on MFM, this study simulates applications of equity market neutral strategies through quantitative techniques over the period Jan.2003 ¡V Dec.2003. The results verified that the three major characteristics of equity market neutral portfolio performance are: 1) providing absolute return; 2) lack of correlation to the equity benchmark; and 3) low volatility due to hedged portfolio structures.

The major purpose of this study is to explore the stock movements of a publicly traded high-frequency trading firm, Virtu Financial. Virtu Financial, as of November 2015, is the only publicly traded high frequency trading firm, offering a opportunity to study the market behavior of a new kind of stock. Since Virtu serves as a unique financial intermediary, my hypothesis is that Virtu should be a market-neutral company since it is able to profit equally in economic upswings and downturns. This study uses a regression based on the Fama and French three factor model, focusing on the influence of the market risk premium, small sized company vs. medium sized company returns, and growth stock vs. value stock returns in changes in inter-daily Virtu Financial returns, These results are then compared to the returns of Virtu’s brokerage competitors, as deemed so by analysts, and CBOE Holding, a company with . The results suggest that Virtu Financial has a market neutral stock, consistent with its means of generating revenue, while its traditional brokerage competitors do not. On the basis of this research, it is concluded that HFT brokerages may present an opportunity to invest in a non-cylcical segment of the finance industry.

Os modelos de otimização de carteiras baseados na análise média-variância apresentam dificuldades para estimação das matrizes de covariância, usadas no processo de otimização, o que leva a necessidade de métodos ad hoc para limitar ou suavizar as alocações eficientes recomendadas pelo modelo. Embora as carteiras obtidas por este método sejam eficientes, não é assegurado que o tracking error seja estacionário, podendo a carteira se distanciar do benchmark, exigindo frequentes recomposições. Neste artigo é empregada a metodologia de cointegração para otimização de carteiras no âmbito de duas estratégias: index tracking e estratégia long-short. A estabilidade das carteiras otimizadas através da cointegração em diferentes cenários de mercado, diminuindo custos relativos a frequentes recomposições da carteira, e níveis de retorno e volatilidade superiores aos benchmarks, mostram que a metodologia é uma ferramenta eficiente e capaz de gerar resultados robustos, se caracterizando como uma atraente ferramenta para a gestão quantitativa de recursos. Modelar a estrutura a termo da taxa de juros é extremamente importante para macroeconomistas e participantes do mercado financeiro em geral. Neste artigo é empregada a formulação de Diebold-Li para ajustar e fazer previsões da estrutura a termo da taxa de juros brasileira. São empregados dados diários referentes às taxas dos contratos de DI Futuro negociados na BM&F que apresentaram maior liquidez para o período de Janeiro de 2006 a Fevereiro de 2009. Diferentemente da maior parte da literatura sobre curva de juros para dados brasileiros, em que o modelo de Diebold- Li é estimado pelo método de dois passos, neste trabalho o modelo é colocado no formado de estado espaço, e os parâmetros são estimados simultaneamente, de forma eficiente, pelo Filtro de Kalman. Os resultados obtidos tanto para o ajuste, mas principalmente no que diz respeito à previsão, mostram que a estimação do modelo através do Filtro de Kalman é a mais adequada, gerando melhores previsões para todas as maturidades quando é considerado horizontes de previsão de um mês, três meses e seis meses. No terceiro artigo artigo nós propomos estimar o modelo dinâmico da estrutura a termo da curva de juros de Nelson e Siegel (1987) considerando duas especificações alternativas. Na primeira, nós consideramos os pesos dos fatores como variantes no tempo e tratamos a heterocedasticidade condicional via um modelo volatilidade estocática com fatores comuns. No segundo caso, consideramos um modelo onde os fatores latentes seguem individualmente processos autoregressivos com volatilidade estocástica. Os assim chamados fatores de volatilidade buscam capturar a incerteza ao longo do tempo associada ao nível, inclinação e curvatura da curva de juros. A estimação é realizada através de métodos de inferência bayesiana, por Markov Chain Monte Carlo. Os resultados mostram que os fatores de volatilidade são altamente persistentes, dando suporte ao fato estilizado de que os choques na volatilidade das taxas de juros são altamente persistentes, e também indicam que o uso de estruturas de volatilidade estocástica levam a melhores ajustes dentro da amostra para a curva de juros observada. / The traditional models to optimize portfolios based on mean-variance analysis aim to determine the portfolio weights that minimize the variance for a certain return level. The covariance matrices used to optimize are difficult to estimate and ad hoc methods often need to be applied to limit or smooth the mean-variance efficient allocations recommended by the model. Although the method is efficient, the tracking error isn’t certainly stationary, so the portfolio can get distant from the benchmark, requiring frequent re-balancements. We used the cointegration methodology to devise two quantitative strategies: index tracking and long-short market neutral. We aim to design optimal portfolios acquiring the asset prices’ co-movements. We used Ibovespa’s index and stocks from Jan-2000 to Dec-2008. The results show that the devise of index tracking portfolios using cointegration generates goods results, replicating the benchmark’s return and volatility. The long-short strategy generated stable returns under several market circumstances, presenting low volatility. Modeling the term structure of interest rate is very important to macroeconomists and financial market practitioners in general. In this paper, we used the Diebold-Li interpretation to the Nelson Siegel model in order to fit and forecast the Brazilian yield curve. The data consisted of daily observations of the most liquid future ID yields traded in the BM&F from January 2006 to February 2009. Differently from the literature on the Brazilian yield curve, where the Diebold-Li model is estimated through the two-step method, the model herein is put in the state-space form, and the parameters are simultaneously and efficiently estimated using the Kalman filter. The results obtained for the fit and for the forecast showed that the Kalman filter is the most suitable method for the estimation of the model, generating better forecast for all maturities when we consider the forecasting horizons of one and three months. In the third essay we propose to estimate the dynamic Nelson-Siegel model of yield curve considering two alternative specifications. At first, we consider the factor loadings such as time-varying conditonal heteroskedasticity and treat via a common factors of stochastic volatility models. In the second case, we consider a model where the latent factors individually following autorregressive process with stochastic volatility. The volatility factors seek to capture the uncertainty over time associated with level, slope and curvature of yield curve.The estimation is performed through bayesian inference, Markov Chain Monte Carlo. The volatility factors showed high persistence, supporting the stylized fact that shocks in the volatility of interest rate are highly persistent, and also indicate that the used of structures of stochastic volatility lead to better in-sample fits of the observed yield curve.

Os modelos de otimização de carteiras baseados na análise média-variância apresentam dificuldades para estimação das matrizes de covariância, usadas no processo de otimização, o que leva a necessidade de métodos ad hoc para limitar ou suavizar as alocações eficientes recomendadas pelo modelo. Embora as carteiras obtidas por este método sejam eficientes, não é assegurado que o tracking error seja estacionário, podendo a carteira se distanciar do benchmark, exigindo frequentes recomposições. Neste artigo é empregada a metodologia de cointegração para otimização de carteiras no âmbito de duas estratégias: index tracking e estratégia long-short. A estabilidade das carteiras otimizadas através da cointegração em diferentes cenários de mercado, diminuindo custos relativos a frequentes recomposições da carteira, e níveis de retorno e volatilidade superiores aos benchmarks, mostram que a metodologia é uma ferramenta eficiente e capaz de gerar resultados robustos, se caracterizando como uma atraente ferramenta para a gestão quantitativa de recursos. Modelar a estrutura a termo da taxa de juros é extremamente importante para macroeconomistas e participantes do mercado financeiro em geral. Neste artigo é empregada a formulação de Diebold-Li para ajustar e fazer previsões da estrutura a termo da taxa de juros brasileira. São empregados dados diários referentes às taxas dos contratos de DI Futuro negociados na BM&F que apresentaram maior liquidez para o período de Janeiro de 2006 a Fevereiro de 2009. Diferentemente da maior parte da literatura sobre curva de juros para dados brasileiros, em que o modelo de Diebold- Li é estimado pelo método de dois passos, neste trabalho o modelo é colocado no formado de estado espaço, e os parâmetros são estimados simultaneamente, de forma eficiente, pelo Filtro de Kalman. Os resultados obtidos tanto para o ajuste, mas principalmente no que diz respeito à previsão, mostram que a estimação do modelo através do Filtro de Kalman é a mais adequada, gerando melhores previsões para todas as maturidades quando é considerado horizontes de previsão de um mês, três meses e seis meses. No terceiro artigo artigo nós propomos estimar o modelo dinâmico da estrutura a termo da curva de juros de Nelson e Siegel (1987) considerando duas especificações alternativas. Na primeira, nós consideramos os pesos dos fatores como variantes no tempo e tratamos a heterocedasticidade condicional via um modelo volatilidade estocática com fatores comuns. No segundo caso, consideramos um modelo onde os fatores latentes seguem individualmente processos autoregressivos com volatilidade estocástica. Os assim chamados fatores de volatilidade buscam capturar a incerteza ao longo do tempo associada ao nível, inclinação e curvatura da curva de juros. A estimação é realizada através de métodos de inferência bayesiana, por Markov Chain Monte Carlo. Os resultados mostram que os fatores de volatilidade são altamente persistentes, dando suporte ao fato estilizado de que os choques na volatilidade das taxas de juros são altamente persistentes, e também indicam que o uso de estruturas de volatilidade estocástica levam a melhores ajustes dentro da amostra para a curva de juros observada. / The traditional models to optimize portfolios based on mean-variance analysis aim to determine the portfolio weights that minimize the variance for a certain return level. The covariance matrices used to optimize are difficult to estimate and ad hoc methods often need to be applied to limit or smooth the mean-variance efficient allocations recommended by the model. Although the method is efficient, the tracking error isn’t certainly stationary, so the portfolio can get distant from the benchmark, requiring frequent re-balancements. We used the cointegration methodology to devise two quantitative strategies: index tracking and long-short market neutral. We aim to design optimal portfolios acquiring the asset prices’ co-movements. We used Ibovespa’s index and stocks from Jan-2000 to Dec-2008. The results show that the devise of index tracking portfolios using cointegration generates goods results, replicating the benchmark’s return and volatility. The long-short strategy generated stable returns under several market circumstances, presenting low volatility. Modeling the term structure of interest rate is very important to macroeconomists and financial market practitioners in general. In this paper, we used the Diebold-Li interpretation to the Nelson Siegel model in order to fit and forecast the Brazilian yield curve. The data consisted of daily observations of the most liquid future ID yields traded in the BM&F from January 2006 to February 2009. Differently from the literature on the Brazilian yield curve, where the Diebold-Li model is estimated through the two-step method, the model herein is put in the state-space form, and the parameters are simultaneously and efficiently estimated using the Kalman filter. The results obtained for the fit and for the forecast showed that the Kalman filter is the most suitable method for the estimation of the model, generating better forecast for all maturities when we consider the forecasting horizons of one and three months. In the third essay we propose to estimate the dynamic Nelson-Siegel model of yield curve considering two alternative specifications. At first, we consider the factor loadings such as time-varying conditonal heteroskedasticity and treat via a common factors of stochastic volatility models. In the second case, we consider a model where the latent factors individually following autorregressive process with stochastic volatility. The volatility factors seek to capture the uncertainty over time associated with level, slope and curvature of yield curve.The estimation is performed through bayesian inference, Markov Chain Monte Carlo. The volatility factors showed high persistence, supporting the stylized fact that shocks in the volatility of interest rate are highly persistent, and also indicate that the used of structures of stochastic volatility lead to better in-sample fits of the observed yield curve.

No / Based on a reduced-form model of credit risk, we explore statistical arbitrage opportunities in the CDS spreads of North American companies. Specifically, we develop a trading strategy using the model to trade market-neutral portfolios while controlling for realistic transaction costs. Empirical results show that our arbitrage strategy is of significant economic value, and also cast doubt on the efficiency of the CDS market. The aggregate returns of the trading strategy are positively related to the square of market-wide credit and liquidity risks, indicating that the market is less efficient when it is more volatile.

Yes / Based on a reduced-form model of credit risk, we explore mispricing in the CDS spreads of North American companies and its economic content. Specifically, we develop a trading strategy using the model to trade out of sample market-neutral portfolios across the term structure of CDS contracts. Our empirical results show that the trading strategy exhibits abnormally large returns, confirming the existence and persistence of a mispricing. The aggregate returns of the trading strategy are positively related to the square of market-wide credit and liquidity risks, indicating that the mispricing is more pronounced when the market is more volatile. When implemented on the Markit data, the strategy shows significant economic value even after controlling for realistic transaction costs.