Online Algorithms for the Portfolio Selection Problem

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. Contents • Performance Evaluation • Selected Algorithms from the Literature • Proposed Algorithms with Risk Management • Empirical Testing of Algorithms• A Software Tool for Testing Target Groups • Scientists and students from the fields of finance, operations research, and machine learning • Practitioners in banks and insurance companies, traders and brokers The Author Dr. Robert Dochow completed his dissertation under the supervision of Prof. Dr. Günter Schmidt at the Chair of Operations Research and Business Informatics of Saarland University, Saarbrücken, Germany.