Online 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.

Robert Dochow mathematically derives a simplified classification structure of selected types of the portfolio selection problem. He proposes two new competitive online algorithms with risk management, which he evaluates analytically. The author empirically evaluates online algorithms by a comprehensive statistical analysis. Concrete results are that follow-the-loser algorithms show the most promising performance when the objective is the maximization of return on investment and risk-adjusted performance. In addition, when the objective is the minimization of risk, the two new algorithms with risk management show excellent performance. A prototype of a software tool for automated evaluation of algorithms for portfolio selection is given.

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.

Embracing finance, economics, operations research, and computers, this book applies modern techniques of analysis and computation to find combinations of securities that best meet the needs of private or institutional investors.

The two-volume set LNAI 8346 and 8347 constitutes the thoroughly refereed proceedings of the 9th International Conference on Advanced Data Mining and Applications, ADMA 2013, held in Hangzhou, China, in December 2013. The 32 regular papers and 64 short papers presented in these two volumes were carefully reviewed and selected from 222 submissions. The papers included in these two volumes cover the following topics: opinion mining, behavior mining, data stream mining, sequential data mining, web mining, image mining, text mining, social network mining, classification, clustering, association rule mining, pattern mining, regression, predication, feature extraction, identification, privacy preservation, applications, and machine learning.

The multi-volume set LNAI 14169 until 14175 constitutes the refereed proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2023, which took place in Turin, Italy, in September 2023. The 196 papers were selected from the 829 submissions for the Research Track, and 58 papers were selected from the 239 submissions for the Applied Data Science Track. The volumes are organized in topical sections as follows: Part I: Active Learning; Adversarial Machine Learning; Anomaly Detection; Applications; Bayesian Methods; Causality; Clustering. Part II: ​Computer Vision; Deep Learning; Fairness; Federated Learning; Few-shot learning; Generative Models; Graph Contrastive Learning. Part III: ​Graph Neural Networks; Graphs; Interpretability; Knowledge Graphs; Large-scale Learning. Part IV: ​Natural Language Processing; Neuro/Symbolic Learning; Optimization; Recommender Systems; Reinforcement Learning; Representation Learning. Part V: ​Robustness; Time Series; Transfer and Multitask Learning. Part VI: ​Applied Machine Learning; Computational Social Sciences; Finance; Hardware and Systems; Healthcare & Bioinformatics; Human-Computer Interaction; Recommendation and Information Retrieval. ​Part VII: Sustainability, Climate, and Environment.- Transportation & Urban Planning.- Demo.

Contains theoretical foundations, applications, and examples of competitive analysis for online algorithms.