This volume investigates algorithmic methods based on machine learning in order to design sequential investment strategies for financial markets. Such sequential investment strategies use information collected from the market's past and determine, at the beginning of a trading period, a portfolio; that is, a way to invest the currently available capital among the assets that are available for purchase or investment. The aim is to produce a self-contained text intended for a wide audience, including researchers and graduate students in computer science, finance, statistics, mathematics, and engineering. Contents:On the History of the Growth-Optimal Portfolio (M M Christensen)Empirical Log-Optimal Portfolio Selections: A Survey (L Györfi, Gy Ottucsák & A Urbán)Log-Optimal Portfolio-Selection Strategies with Proportional Transaction Costs (L Györfi & H Walk)Growth-Optimal Portfolio Selection with Short Selling and Leverage (M Horváth & A Urbán)Nonparametric Sequential Prediction of Stationary Time Series (L Györfi & G Ottuscák)Empirical Pricing American Put Options (L Györfi & A Telcs) Readership: Researchers, academics and graduate students in artificial intelligence/machine learning, and mathematical finance/quantitative finance. Keywords:Log-Optimal Portfolio;Growth-Optimal Portfolio;Sequential Investment Strategies for Financial MarketsKey Features:Covers machine learning algorithms for the aggregation of elementary investment strategiesHighlights multi-period and multi-asset tradingFocuses on nonparametric estimation of the underlying distributions in the market process