Portfolio Selection

With the aim to sequentially determine optimal allocations across a set of assets, Online Portfolio Selection (OLPS) has significantly reshaped the financial investment landscape. Online Portfolio Selection: Principles and Algorithms supplies a comprehensive survey of existing OLPS principles and presents a collection of innovative strategies that leverage machine learning techniques for financial investment. The book presents four new algorithms based on machine learning techniques that were designed by the authors, as well as a new back-test system they developed for evaluating trading strategy effectiveness. The book uses simulations with real market data to illustrate the trading strategies in action and to provide readers with the confidence to deploy the strategies themselves. The book is presented in five sections that: Introduce OLPS and formulate OLPS as a sequential decision task Present key OLPS principles, including benchmarks, follow the winner, follow the loser, pattern matching, and meta-learning Detail four innovative OLPS algorithms based on cutting-edge machine learning techniques Provide a toolbox for evaluating the OLPS algorithms and present empirical studies comparing the proposed algorithms with the state of the art Investigate possible future directions Complete with a back-test system that uses historical data to evaluate the performance of trading strategies, as well as MATLAB® code for the back-test systems, this book is an ideal resource for graduate students in finance, computer science, and statistics. It is also suitable for researchers and engineers interested in computational investment. Readers are encouraged to visit the authors’ website for updates: http://olps.stevenhoi.org.

In our daily life, almost every family owns a portfolio of assets. This portfolio could contain real assets such as a car, or a house, as well as financial assets such as stocks, bonds or futures. Portfolio theory deals with how to form a satisfied portfolio among an enormous number of assets. Originally proposed by H. Markowtiz in 1952, the mean-variance methodology for portfolio optimization has been central to the research activities in this area and has served as a basis for the development of modem financial theory during the past four decades. Follow-on work with this approach has born much fruit for this field of study. Among all those research fruits, the most important is the capital asset pricing model (CAPM) proposed by Sharpe in 1964. This model greatly simplifies the input for portfolio selection and makes the mean-variance methodology into a practical application. Consequently, lots of models were proposed to price the capital assets. In this book, some of the most important progresses in portfolio theory are surveyed and a few new models for portfolio selection are presented. Models for asset pricing are illustrated and the empirical tests of CAPM for China's stock markets are made. The first chapter surveys ideas and principles of modeling the investment decision process of economic agents. It starts with the Markowitz criteria of formulating return and risk as mean and variance and then looks into other related criteria which are based on probability assumptions on future prices of securities.

This uniquely comprehensive guide provides expert insights into everything from financial mathematics to the practical realities of asset allocation and pricing Investors like you typically have a choice to make when seeking guidance for portfolio selection―either a book of practical, hands-on approaches to your craft or an academic tome of theories and mathematical formulas. From three top experts, Portfolio Selection and Asset Pricing strikes the right balance with an extensive discussion of mathematical foundations of portfolio choice and asset pricing models, and the practice of asset allocation. This thorough guide is conveniently organized into four sections: Mathematical Foundations―normed vector spaces, optimization in discrete and continuous time, utility theory, and uncertainty Portfolio Models―single-period and continuous-time portfolio choice, analogies, asset allocation for a sovereign as an example, and liability-driven allocation Asset Pricing―capital asset pricing models, factor models, option pricing, and expected returns Robust Asset Allocation―robust estimation of optimization inputs, such as the Black-Litterman Model and shrinkage, and robust optimizers Whether you are a sophisticated investor or advanced graduate student, this high-level title combines rigorous mathematical theory with an emphasis on practical implementation techniques.

This book consists of eight chapters, authored by distinguished researchers and practitioners, that highlight the state of the art and recent trends in addressing the project portfolio selection and scheduling problem (PPSSP) across a variety of domains, particularly defense, social programs, supply chains, and finance. Many organizations face the challenge of selecting and scheduling a subset of available projects subject to various resource and operational constraints. In the simplest scenario, the primary objective for an organization is to maximize the value added through funding and implementing a portfolio of projects, subject to the available budget. However, there are other major difficulties that are often associated with this problem such as qualitative project benefits, multiple conflicting objectives, complex project interdependencies, workforce and manufacturing constraints, and deep uncertainty regarding project costs, benefits, and completion times. It is well known that the PPSSP is an NP-hard problem and, thus, there is no known polynomial-time algorithm for this problem. Despite the complexity associated with solving the PPSSP, many traditional approaches to this problem make use of exact solvers. While exact solvers provide definitive optimal solutions, they quickly become prohibitively expensive in terms of computation time when the problem size is increased. In contrast, evolutionary and memetic computing afford the capability for autonomous heuristic approaches and expert knowledge to be combined and thereby provide an efficient means for high-quality approximation solutions to be attained. As such, these approaches can provide near real-time decision support information for portfolio design that can be used to augment and improve existing human-centric strategic decision-making processes. This edited book provides the reader with a broad overview of the PPSSP, its associated challenges, and approaches to addressing the problem using evolutionary and memetic computing.

Applies modern techniques of analysis and computation to the problem of finding combinations of securities that best meet the needs of the private institutional investor. Written primarily with the nonmathematician in mind, although it contains mathematical development of the subject in appendixes.

This book provides both practitioners and academics with a scientific approach to portfolio selection using Goal Programming, an approach which is capable as far as is possible of achieving a required set of preferences deemed appropriate by a decision maker. Goal Programming is perhaps the most widely-used approach in the field of multiple criteria decision-making that enables the decision maker to incorporate numerous variations of constraints and goals. The original portfolio selection problem, with risk and return optimisation, can be viewed as a case of Goal Programming with two objectives. Additional objectives representing other factors, such as liquidity, can be introduced for a more realistic approach to portfolio selection problems. This book comes in a time where scientific frameworks for investment decision-making are absolutely necessary, that is after the recent financial and economic crisis; where irrational decisions and a misuse of mathematical models had equally fed into the spiral of the financial crisis. The real-world decision problems are usually changeable, complex and resist treatment with conventional approaches. Therefore, the optimisation of a single objective subject to a set of rigid constraints is in most cases unrealistic, and that is why Goal Programming was introduced, in an attempt to eliminate or at least mitigate this shortcoming. Most mathematical models are based on very strong theoretical assumptions which are not entirely respected by markets in practice. In contrast, Goal Programming models are based on real-world cases where the most feasible solution is sought as opposed to an ideal simplified solution. Therefore, this book provides practitioners with a new and superior scientific framework for investment decision-making, while aiming to stimulate further research and development. Moreover, the book provides scientific approaches for portfolio selection with Goal Programming, which will provide added value for practitioners in complementing their financial expertise with a sound scientific decision-making framework.

In 1952, Harry Markowitz published "Portfolio Selection," a paper which revolutionized modern investment theory and practice. The paper proposed that, in selecting investments, the investor should consider both expected return and variability of return on the portfolio as a whole. Portfolios that minimized variance for a given expected return were demonstrated to be the most efficient. Markowitz formulated the full solution of the general mean-variance efficient set problem in 1956 and presented it in the appendix to his 1959 book, Portfolio Selection. Though certain special cases of the general model have become widely known, both in academia and among managers of large institutional portfolios, the characteristics of the general solution were not presented in finance books for students at any level. And although the results of the general solution are used in a few advanced portfolio optimization programs, the solution to the general problem should not be seen merely as a computing procedure. It is a body of propositions and formulas concerning the shapes and properties of mean-variance efficient sets with implications for financial theory and practice beyond those of widely known cases. The purpose of the present book, originally published in 1987, is to present a comprehensive and accessible account of the general mean-variance portfolio analysis, and to illustrate its usefulness in the practice of portfolio management and the theory of capital markets. The portfolio selection program in Part IV of the 1987 edition has been updated and contains exercises and solutions.