在資產組合的優化過程中，總是希望賺取穩定的報酬以及規避不必要的風險，也因此，風險的衡量在資產組合理論中至關重要，而A. Ahmadi-Javid(2011)發表證明以相對熵為基礎的熵風險值(Entropic Value-at-Risk，簡稱EVaR)是為被廣泛使用的條件風險值(Conditional Value-at-Risk，簡稱CVaR)之上界，且EVaR在使用上更為效率，具有相當優越的性質，而本文將利用熵風險值的約當測度，去修改傳統均值–變異模型，並以臺灣股市為例，利用基因模擬退火混合演算法來驗證其在動態架構下的性質及績效，結果顯示比起傳統模型更為貼近效率前緣。

Student Number : 9005994G - MSc research report - School of Construction Economics and Management - Faculty of Engineering and the Built Environment / The objectives of this research are to assess the returns, risks and correlation of a mixed-asset portfolio, establish the role of real estate in a mixed-asset portfolio and suggest an appropriate real estate allocation in the South African pension fund industry. The issue of low real estate allocation has been a subject of interest to practitioners and academics, both locally and internationally, despite the diversification benefit that real estate provides in a mixed-asset portfolio. A statistical approach was considered most the appropriate tool for analyzing returns. Solver optimizer in the excel spreadsheet package was used to generate efficient frontiers and the associated values of portfolios. Real estate provided a lower return of 1.25% and a lower standard deviation of 4.90% compared to equities with a return of 1.39% and the highest standard deviation of 6.23%, whilst bonds provided the best risk-return trade off, with a return of 1.42% and the lowest standard deviation of 2.64%. An equally -weighted portfolio consisting of bonds and stocks and a portfolio consisting bonds, stocks and real estate was simulated. The equally -weighted portfolio of bonds and stocks provides a return of 1.41% and a standard deviation of 3.76%. The minimum variance with bias to bonds provides a higher return of 1.42% at a lower level of risk of 2.62%. The equally -weighted portfolio consisting of bonds, stocks and real estate provides a return of 1.35%, with a lower risk of 3.49%. The minimum variance with bias to bonds provides almost the same return of 1.40% at a lower level of risk of 2.54% compared to the bond and share portfolio. The Chi-Square statistical tool was used to test the diversification benefit of real estate. It can be concluded that the standard deviation of the portfolio with property is close enough to the standard deviation without property of 3.76% and cannot statistically say that it is different given the 5% level of significance. The Sharpe ratio was used to test the favourable risk adjusted returns offered by real estate. It concluded that property provides favourable risk adjusted returns and diversification benefits, as illustrated with the increasing portfolio return from 7.44% to 8.66% on Sharpe ratio basis and standard deviation of the portfolio decreasing from 3.76% to 2.54%. The literature review generally supported the view that real estate has a role in a mixed-asset portfolio. Research topics such as securitized versus unsecuritized real estate, real estate allocation and diversification, returns and risk, inflation hedging, modern portfolio theory and the efficient -frontier were analysed and related to the research report. The empirical analysis supports the hypothesis that real estate provides diversification benefits. The property cycle is positive and it is supported by positive property fundamentals like (vacancies are at lowest levels, capitalisation rates are strengthening, the property cycle is turning positive and a stable interest rate environment). The positive property fundamentals will lead to earnings growth. An allocation of between 10% based on the lower end of the minimum variance and 15% based on the lower end of the risk/return ratio is recommended for a mixed-asset portfolio.

<p>Hedge funds are a debated subject in today’s financial industry. During 2008, despite hedge funds absolute return target, the global hedge fund industry showed a negative performance whilst the Swedish hedge fund market performed relatively well in comparison. Many studies have been made investigating the effect on incorporating hedge funds in a traditional portfolio though none focused separately on the Swedish market. In a global perspective it is quite easy to invest in hedge fund portfolios due to the existence of investable indices. To invest on the Swedish market is a more complex matter. SIX Harcourt HFXS Index is a Swedish hedge fund index representing the Swedish hedge fund market though it is not investable. Hence it would be interesting to see if it is possible to create an investable version of SIX Harcourt HFXS. When creating an investable index, several administrative costs will arise and in order to cover these costs it would be interesting to see whether or not it possible to optimize SIX Harcourt HFXS Index in purpose of achieving a outperformance which could cover any administrative costs for setting up the investable version. Also, since the optimized version must replicate the standard SIX Harcourt HFXS Index it must maintain a certain level of correlation.</p><p>This thesis, which is based on a positivistic epistemology, is built upon a quantitative case study where SIX Harcourt HFXS Index is optimized in purpose of achieving an outperformance in terms of the risk-adjusted return. The optimization uses an adjusted mean-variance methodology and is limited to a maintained correlation above 0,9 towards the standard SIX Harcourt HFXS Index. The optimization is created through the use of an Excel application created by Harcourt Investment Consulting.</p><p>Also, based on the outperformance by Swedish hedge funds compared to global hedge funds, this study aims to show the effect of incorporating Swedish hedge funds in a traditional portfolio consisting of equities and bonds. This effect is analyzed by the use of several performance-and risk measures.</p><p>The study shows that it is possible to optimize SIX Harcourt HFXS Index and produce an outperformance of approximately 1,5% per annum with a maintained correlation above 0,9. It also shows that the effect of incorporating Swedish hedge funds to a traditional portfolio is positive in regards to both risk and return.</p>

Hedge funds are a debated subject in today’s financial industry. During 2008, despite hedge funds absolute return target, the global hedge fund industry showed a negative performance whilst the Swedish hedge fund market performed relatively well in comparison. Many studies have been made investigating the effect on incorporating hedge funds in a traditional portfolio though none focused separately on the Swedish market. In a global perspective it is quite easy to invest in hedge fund portfolios due to the existence of investable indices. To invest on the Swedish market is a more complex matter. SIX Harcourt HFXS Index is a Swedish hedge fund index representing the Swedish hedge fund market though it is not investable. Hence it would be interesting to see if it is possible to create an investable version of SIX Harcourt HFXS. When creating an investable index, several administrative costs will arise and in order to cover these costs it would be interesting to see whether or not it possible to optimize SIX Harcourt HFXS Index in purpose of achieving a outperformance which could cover any administrative costs for setting up the investable version. Also, since the optimized version must replicate the standard SIX Harcourt HFXS Index it must maintain a certain level of correlation. This thesis, which is based on a positivistic epistemology, is built upon a quantitative case study where SIX Harcourt HFXS Index is optimized in purpose of achieving an outperformance in terms of the risk-adjusted return. The optimization uses an adjusted mean-variance methodology and is limited to a maintained correlation above 0,9 towards the standard SIX Harcourt HFXS Index. The optimization is created through the use of an Excel application created by Harcourt Investment Consulting. Also, based on the outperformance by Swedish hedge funds compared to global hedge funds, this study aims to show the effect of incorporating Swedish hedge funds in a traditional portfolio consisting of equities and bonds. This effect is analyzed by the use of several performance-and risk measures. The study shows that it is possible to optimize SIX Harcourt HFXS Index and produce an outperformance of approximately 1,5% per annum with a maintained correlation above 0,9. It also shows that the effect of incorporating Swedish hedge funds to a traditional portfolio is positive in regards to both risk and return.

Many optimal stochastic control problems in finance can be formulated in the form of Hamilton-Jacobi-Bellman (HJB) partial differential equations (PDEs). In this thesis, a general framework for solutions of HJB PDEs in finance is developed, with application to asset allocation. The numerical scheme has the following properties: it is unconditionally stable; convergence to the viscosity solution is guaranteed; there are no restrictions on the underlying stochastic process; it can be easily extended to include features as needed such as uncertain volatility and transaction costs; and central differencing is used as much as possible so that use of a locally second order method is maximized. In this thesis, continuous time mean variance type strategies for dynamic asset allocation problems are studied. Three mean variance type strategies: pre-commitment mean variance, time-consistent mean variance, and mean quadratic variation, are investigated. The numerical method can handle various constraints on the control policy. The following cases are studied: allowing bankruptcy (unconstrained case), no bankruptcy, and bounded control. In some special cases where analytic solutions are available, the numerical results agree with the analytic solutions. These three mean variance type strategies are compared. For the allowing bankruptcy case, analytic solutions exist for all strategies. However, when additional constraints are applied to the control policy, analytic solutions do not exist for all strategies. After realistic constraints are applied, the efficient frontiers for all three strategies are very similar. However, the investment policies are quite different. These results show that, in deciding which objective function is appropriate for a given economic problem, it is not sufficient to simply examine the efficient frontiers. Instead, the actual investment policies need to be studied in order to determine if a particular strategy is applicable to specific investment problem.

Many optimal stochastic control problems in finance can be formulated in the form of Hamilton-Jacobi-Bellman (HJB) partial differential equations (PDEs). In this thesis, a general framework for solutions of HJB PDEs in finance is developed, with application to asset allocation. The numerical scheme has the following properties: it is unconditionally stable; convergence to the viscosity solution is guaranteed; there are no restrictions on the underlying stochastic process; it can be easily extended to include features as needed such as uncertain volatility and transaction costs; and central differencing is used as much as possible so that use of a locally second order method is maximized. In this thesis, continuous time mean variance type strategies for dynamic asset allocation problems are studied. Three mean variance type strategies: pre-commitment mean variance, time-consistent mean variance, and mean quadratic variation, are investigated. The numerical method can handle various constraints on the control policy. The following cases are studied: allowing bankruptcy (unconstrained case), no bankruptcy, and bounded control. In some special cases where analytic solutions are available, the numerical results agree with the analytic solutions. These three mean variance type strategies are compared. For the allowing bankruptcy case, analytic solutions exist for all strategies. However, when additional constraints are applied to the control policy, analytic solutions do not exist for all strategies. After realistic constraints are applied, the efficient frontiers for all three strategies are very similar. However, the investment policies are quite different. These results show that, in deciding which objective function is appropriate for a given economic problem, it is not sufficient to simply examine the efficient frontiers. Instead, the actual investment policies need to be studied in order to determine if a particular strategy is applicable to specific investment problem.

In an ever-changing global environment, the ability to adapt to the current economic climate is essential for a company to prosper and survive. Numerous previous re- search state that better risk management and low overall risks will lead to a higher firm value. The purpose of this study is to examine if portfolio theory, made for fi- nancial portfolios, can be used to compose product portfolios in order to minimize risk and optimize returns. The term contingent hedge is defined as an optimal portfolio that can be identified today, that in the future will yield a stable stream of returns at a low level of risk. For companies that might engage in costly hedging activities on the futures market, the benefits of creat- ing a contingent hedge are several. These include creating an optimized portfolio that minimizes risk and avoid trading contracts on futures markets that would incur hefty transaction costs and risks. Using quantitative financial models, product portfolio compositions are generated and compared with the returns and risks profile of individual commodities, as well as the actual product portfolio compositions of publicly traded mining companies. Us- ing Modern Portfolio Theory an efficient frontier is generated, yielding two inde- pendent portfolios, the minimum risk portfolio and the tangency portfolio. The Black-Litterman model is also used to generate yet another portfolio using a Bayesian approach. The portfolios are generated by historic time-series data and compared with the actual future development of commodities; the portfolios are then analyzed and compared. The results indicate that the minimum risk portfolio provides a signif- icantly lower risk than the compositions of all mining companies in the study, as well as the risks of individual commodities. This in turn will lead to several benefits for company management and the firm’s shareholders that are discussed throughout the study. However, as for a return-optimizing portfolio, no significant results can be found. Furthermore, the analysis suggests a series of improvements that could potentially yield an even greater result. The recommendation is that mining companies can use the methods discussed throughout this study as a way to generate a costless contin- gent hedge, rather than engage in hedging activities on futures markets.

確定提撥制是現今退休金制度潮流的趨勢，而在這個制度下，勞工最後所能累積的退休金總額及每月所能領到的月退休金額度和個人帳戶的投資結果有很大的關係，所以個人帳戶的投資績效成為勞工退休生活安全性最重要的因素。 本研究的目的在提供一個方法以評量投資績效，使得在每月提撥一定金額到個人帳戶的情形下，對於投資期間的經濟環境以隨機投資模型或情境分析模型加以考量後，可以在不同的投資策略及起始資產配置下，找到適合投資人的最佳投資策略及起始資產配置。在本研究中考慮了股票和長期債券兩種投資標的，而投資標的之投資報酬率變化則以隨機投資模型(Stochastic Investment Model)及情境分析(Scenario Analysis)兩種模擬方式為之，其中在隨機投資模型模擬的部分，不同的隨機投資模型對於經濟環境有不同的設定，也因此將得到不同的投資結果，本研究採用在英國學術上廣為研究的Wilkie投資模型(1986)及黃泓智等人於2005年證券市場發展季刊所推導之台灣投資模型，並利用蒙地卡羅模擬的方式來建構投資標的之報酬率。而在情境分析模擬的部分，則設定三種基本的投資報酬率趨勢，並假設三種投資報酬率趨勢服從均勻分配，而後考慮投資期間分成前後兩個時期，搭配而得九種情境。 本文將觀察不同的起始資產配置(股票資產配置之權重考慮由0%~100%，間隔為1%，共101組；債券資產的權重則為1-股票資產配置之權重，也就是100%~0%)，並以投資組合保險中三種常見的投資策略：買入持有(Buy & Hold；BH)、固定比例混合法(Constant Mixture；CM)及時間不變性投資組合保護(Time-invariant Portfolio Protection；TIPP)，作為投資策略。 在三種投資策略及每種投資策略有101個起始資產配置下，將可以得到303組不同的投資結果，而每一組投資結果中，都可找到個人帳戶於退休時的累積金額、在一定目標所得替代率下之破產機率，以及平均投資報酬率和投資報酬率之標準差，並將所得之投資組合報酬率之平均值為縱軸，標準差為橫軸作圖，找出效率前緣；也就是說，可以依個人帳戶持有人的風險，在其所能忍受的風險下，找到最適的起始資產配置及投資策略，及依這樣的起始資產配置和投資策略下所能得到的平均報酬。另外，更進一步以Sharpe ratio及Reward-to-VaR ratio、Reward-to-CTE ratio三個指標來衡量投資表現，找出在這三個指標下的最適起始資產配置和投資策略。 在前述中，都未考慮到交易成本對於投資結果的影響，但在現實的環境中，交易成本對於投資結果是有影響的，所以本研究也會在考慮交易成本下，找到情境分析和隨機模型下的投資結果及效率前緣，並找出三個投資指標的值來衡量投資表現。 / The defined contribution plan is the trend of retirement pension funds management, but under this plan, the total account values accumulated and the retirement benefits paid each month that labors can get are great related to the investment results of the individual accounts. That's why we said that the investment result of the individual accounts is the most important factor the labors care about. In this article, we will focus on the measure of investment results. We consider bond and stock as our holding assets, and set the investment rate of return in two methods, including scenario analysis and stochastic model. In the scenario analysis method, we set fourteen scenarios to reflect the changes of the investment returns of stocks. In the stochastic model method, we take use of Wilkie investment model to set the investment return rate of stocks and bonds and simulate enormous data to find the average investment rate of return. In each method, we will consider 101 different initial ratio of stock value and three different investment strategies: Buy & Hold(BH)、Constant Mixture(CM) and Time-invariant Portfolio Protection(TIPP). After setting the investment rate of return and investment strategies, we can find 303 different investment results under three investment strategies and 101 initial ratios of stock values. In each result, we can get the accumulated amounts, the income substitute rate and the average rate of return, and use the average rate of return as y-axis, standard deviation as x-axis to find the efficient frontier. That is, we can find the optimal investment strategies and initial ratio of stock value under the risk we can tolerant. We will also use Sharpe Ratio、Reward-to-VaR ratio and Reward-to-CTE ratio to measure the investment results, and find the optimal investment strategies and initial ratio of stock value basic on the three ratios. In practice, the transaction cost is an important factor that will affect the investment results, so we also find the investment results under different situations which had considered the transaction cost.

In this thesis we investigate the application of two heuristic methods, genetic algorithms and tabu/scatter search, to the optimisation of realistic portfolios. The model is based on the classical mean-variance approach, but enhanced with floor and ceiling constraints, cardinality constraints and nonlinear transaction costs which include a substantial illiquidity premium, and is then applied to a large I 00-stock portfolio. It is shown that genetic algorithms can optimise such portfolios effectively and within reasonable times, without extensive tailoring or fine-tuning of the algorithm. This approach is also flexible in not relying on any assumed or restrictive properties of the model and can easily cope with extensive modifications such as the addition of complex new constraints, discontinuous variables and changes in the objective function. The results indicate that that both floor and ceiling constraints have a substantial negative impact on portfolio performance and their necessity should be examined critically relative to their associated administration and monitoring costs. Another insight is that nonlinear transaction costs which are comparable in magnitude to forecast returns will tend to diversify portfolios; the effect of these costs on portfolio risk is, however, ambiguous, depending on the degree of diversification required for cost reduction. Generally, the number of assets in a portfolio invariably increases as a result of constraints, costs and their combination. The implementation of cardinality constraints is essential for finding the bestperforming portfolio. The ability of the heuristic method to deal with cardinality constraints is one of its most powerful features. / Decision Sciences / M. Sc. (Operations Research)

Orientador: Luziane Ferreira de Mendonça / Dissertação (mestrado profissional) - Universidade Estadual de Campinas, Instituto de Matemática, Estatística e Computação Científica / Made available in DSpace on 2018-08-17T11:31:02Z (GMT). No. of bitstreams: 1 Soares_VanessadeCarvalhoAlves_M.pdf: 1540180 bytes, checksum: 198ad552da53ca9cbe2fd6bf7fc77c17 (MD5) Previous issue date: 2011 / Resumo: Neste trabalho, propomos a determinação de uma carteira de investimento ótima via um método sem derivada. Para isso, utilizamos o modelo de média-variância proposto por Harry M. Markowitz. no qual o problema é formulado de modo a se minimizar o risco do portfolio para um dado nível de retorno esperado, ou maximizar o nível de retorno fixado do portfolio associado a um dado nível de risco e determinar todas as carteiras ótimas, no sentido risco e retorno, formando a Fronteira Eficiente. Nosso algoritmo é baseado no Método Nelder-Mead, destinado à resolução de problemas de programação não linear irrestritos. Assim, adequamos a formulação do portfolio, que depende de restrições, para a utilização do mesmo. / Abstract: In this work we perform a portfolio optimization by using a derivative-free method. For this, we use the Mean-Variance Analysis proposed by Harry M. Markowitz, in which the problem is formulated as one of minimizing portfolio risk subject to a targeted expected portfolio return. Or, for a particular level of risk, we can find a combination of assets that is going to give the highest expected return and determine all the optimal portfolios, towards risk and return, forming the Efficient Frontier. Our algorithm is based on Nelder-Mead method, for solving problems of unconstrained nonlinear programming. Therefore, the formulation of the portfolio, subject to constraints, was adapted for its use. / Mestrado / Mestre em Matemática