This self-contained text on online portfolio selection (OLPS) is intended for graduate students in finance, computer science, and statistics, as well as researchers and engineers interested in
computational investment. Coverage encompasses fundamentals of OLPS for financial investments and machine learning techniques for financial investment. Principles discussed include follow the
winner, follow the loser, pattern matching, and meta-learning. Examples with simulated data are used demonstrate trading strategies. The text provides four original algorithms and a backtest
system for determining how well trading strategies work, as well as empirical results on evaluation of cumulative wealth, risk and risk-adjusted return, and parameter sensitivity. Numerous
b&w charts and diagrams are included. About 60 pages of appendices offer code and instructions for OLPS, proofs and derivations, supplementary data, and portfolio statistics. A companion
web site is available. Annotation ©2016 Ringgold, Inc., Portland, OR (protoview.com)
