Online Portfolio Selection: Principles and Algorithms

Online Portfolio Selection (OLPS) is a method that uses machine learning techniques to optimize asset allocations. This book provides a comprehensive survey of OLPS principles and algorithms, including four new algorithms based on machine learning techniques, and a back-test system for evaluating trading strategy effectiveness. It is an ideal resource for graduate students in finance, computer science, and statistics, as well as researchers and engineers interested in computational investment.

Format: Paperback / softback
Length: 230 pages
Publication date: 31 January 2024
Publisher: Taylor & Francis Ltd

Online Portfolio Selection (OLPS) has revolutionized the financial investment landscape by enabling the sequential determination of optimal allocations across a diverse range of assets. This comprehensive text, titled Online Portfolio Selection: Principles and Algorithms, provides a thorough exploration of existing OLPS principles and showcases a collection of cutting-edge strategies that harness the power of machine learning techniques for financial investment.

The book offers a comprehensive survey of OLPS principles, encompassing benchmarks, follow-the-winner, follow-the-loser, pattern matching, and meta-learning. It introduces four novel algorithms developed by the authors, along with a novel back-test system designed to evaluate the effectiveness of trading strategies. These algorithms are based on cutting-edge machine learning techniques and are accompanied by a toolbox for assessing their performance.

Furthermore, the book includes empirical studies comparing the proposed OLPS algorithms with the state-of-the-art, reinforcing their efficacy and reliability. The text is organized into five sections, each dedicated to a specific aspect of OLPS. The first section introduces OLPS and frames it as a sequential decision-making task. The subsequent sections delve into key OLPS principles, including benchmarks, follow-the-winner, follow-the-loser, pattern matching, and meta-learning.

The fourth section presents the innovative OLPS algorithms, highlighting their unique features and advantages. The final section offers a comprehensive toolbox for evaluating the proposed OLPS algorithms, along with empirical studies comparing their performance with existing methods.

To enhance accessibility, the book includes a back-test system that utilizes historical data to evaluate the performance of trading strategies. Additionally, MATLAB® code for the back-test systems is provided, making it an invaluable resource for graduate students in finance, computer science, and statistics. Researchers and engineers interested in computational investment will also find this book to be of great interest.

To stay updated on the latest developments in OLPS, readers are encouraged to visit the authors' website: http://olps.stevenhoi.org. This website offers additional resources, including research papers, case studies, and examples, to further enrich their understanding of this evolving field.

In conclusion, Online Portfolio Selection: Principles and Algorithms is a comprehensive and authoritative text that offers a deep understanding of OLPS principles and their application in financial investment. By leveraging machine learning techniques, the book empowers readers to develop innovative strategies and make informed investment decisions. Whether you are a student, researcher, or professional in the finance industry, this book is an essential resource for advancing your knowledge and expertise in OLPS.

Weight: 426g
Dimension: 234 x 156 (mm)
ISBN-13: 9781138894105