Evolving Rule-Based Trading Systems

Created by W.Langdon from gp-bibliography.bib Revision:1.4420

  title =        "Evolving Rule-Based Trading Systems",
  author =       "Christian Setzkorn and Laura Dipietro and 
                 Robin Purshouse",
  institution =  "Department of Computer Science, University of
  year =         "2002",
  number =       "ULCS-02-005",
  address =      "UK",
  keywords =     "genetic algorithms, genetic programming",
  citeseer-isreferencedby = "oai:CiteSeerPSU:78975",
  citeseer-references = "oai:CiteSeerPSU:212034;
  annote =       "The Pennsylvania State University CiteSeer Archives",
  language =     "en",
  oai =          "oai:CiteSeerPSU:503310",
  rights =       "unrestricted",
  URL =          "http://www.csc.liv.ac.uk/research/techreports/tr2002/tr02005abs.html",
  URL =          "http://www.csc.liv.ac.uk/research/techreports/tr2002/ulcs-02-005.ps",
  URL =          "http://citeseer.ist.psu.edu/503310.html",
  abstract =     "In this study, a market trading rulebase is optimised
                 using genetic programming (GP). The rulebase is
                 comprised of simple relationships between technical
                 indicators, and generates signals to buy, sell short,
                 and remain inactive. The methodology is applied to
                 prediction of the Standard & Poor's composite index
                 (02-Jan-1990 to 18-Oct-2001). Two potential market
                 systems are inferred: a simple system using few rules
                 and nodes, and a more complex system. Results are
                 compared with a benchmark buy-and-hold strategy.
                 Neither trading system was found capable of
                 consistently outperforming this benchmark. More
                 complicated rulebases, in addition to being difficult
                 to understand, are susceptible to overfitting. Simpler
                 rulebases are more robust to changing market
                 conditions, but cannot take advantage of
                 high-profit-making opportunities. By increasing the
                 richness of the available rulebase building-blocks and
                 the variety of training data, it is anticipated that
                 subsequent systems will surpass the benchmark
  size =         "10 pages",

Genetic Programming entries for Christian Setzkorn Laura Dipietro Robin Purshouse