Abstract

A new approach to algorithmic trading system development is presented. This approach, Kernel Price Pattern Trading (KPPTP ), allows the practitioner to link the performance of a learned classifier (that predicts the occurrence of the price pattern P) to the profitability of the system. A positive definite kernel based distance that tries to capture the drivers of the process of price patterns formation and some results about the profitability of the system are also presented. © 2007 Springer Science+Business Media, LLC.