Parallell Evolution of Trading Strategies Based on Binary Classification Using Sub-Machine-Code Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.3872

@InProceedings{svangard:2002:SEAL,
  author =       "Nils Svangard and Peter Nordin and Stefan Lloyd",
  title =        "Parallell Evolution of Trading Strategies Based on
                 Binary Classification Using Sub-Machine-Code Genetic
                 Programming",
  booktitle =    "Proceedings of the 4th Asia-Pacific Conference on
                 Simulated Evolution And Learning (SEAL'02)",
  year =         "2002",
  editor =       "Lipo Wang and Kay Chen Tan and Takeshi Furuhashi and 
                 Jong-Hwan Kim and Xin Yao",
  address =      "Orchid Country Club, Singapore",
  month =        "18-22 " # nov,
  keywords =     "genetic algorithms, genetic programming",
  ISBN =         "981-04-7522-5",
  abstract =     "In this paper we represent the market as a binary
                 classification problem and evolve two trading
                 strategies that look for buy and sell opportunities in
                 parallel. Investment decisions are then based on both
                 strategies using different voting systems. Our system
                 uses a large number binary signals based technical
                 analysis as input. This allows us to increase the
                 execution speed over 100 times using a sub-machine-code
                 genetic programming system that evaluate 128 fitness
                 cases in parallel. We believe that this is the first
                 work that explicitly treats trading as a classification
                 problem and uses sub-machine-code genetic programming
                 to evolve multiple trading strategies used in a voting
                 system. The strategies we find generalise well and
                 outperform the buy-and-hold strategy on unseen data. We
                 find that the multiple strategy voting system reduces
                 risk but also the return on investment. We also find
                 several correlations between instruments from technical
                 analysis and the future share price that appear
                 frequently in the most successful strategies.",
  notes =        "SEAL 2002 see
                 http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.200.6410&rep=rep1&type=pdf",
}

Genetic Programming entries for Nils Svangard Peter Nordin Stefan Lloyd

Citations