An Additive On-Line Portfolio Selection Algorithm

Abstract

An on-line portfolio management algorithm using additive update rule is presented with consideration of proportional transaction costs. After establishing a relationship between transaction costs and the distance of two portfolio vectors, we solve an optimization problem making a balance between high wealth growth rate and low transaction costs. It is shown that the presented portfolio strategy is universal relative to the set of all buy-and-hold portfolios in the sense that it achieves the same asymptotic exponential growth rate of wealth as the best buy-and-hold portfolio determined with hindsight. The simulation examples using the real data from the London Stock Exchange show the efficiency and the computational simplicity of the algorithm.