Kernel price pattern trading

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. Keywords Kernels

• Type: Journal
• Year: 2008
• Where: APIN
• Authors: Alejandro Cañete, Jorge Constanzo, Luis Salinas
• Keywords: APIN 2008, Price Pattern, Price Pattern Trading, Trading System Development