Overfitting or Poor Learning: A Critique of Current Financial Applications of GP

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

  author =       "Shu-Heng Chen and Tzu-Wen Kuo",
  title =        "Overfitting or Poor Learning: A Critique of Current
                 Financial Applications of GP",
  booktitle =    "Genetic Programming, Proceedings of EuroGP'2003",
  year =         "2003",
  editor =       "Conor Ryan and Terence Soule and Maarten Keijzer and 
                 Edward Tsang and Riccardo Poli and Ernesto Costa",
  volume =       "2610",
  series =       "LNCS",
  pages =        "34--46",
  address =      "Essex",
  publisher_address = "Berlin",
  month =        "14-16 " # apr,
  organisation = "EvoNet",
  publisher =    "Springer-Verlag",
  keywords =     "genetic algorithms, genetic programming",
  ISBN =         "3-540-00971-X",
  URL =          "http://www.springerlink.com/openurl.asp?genre=article&issn=0302-9743&volume=2610&spage=34",
  DOI =          "doi:10.1007/3-540-36599-0_4",
  abstract =     "Motivated by a measure of predictability, this paper
                 uses the extracted signal ratio as a measure of the
                 degree of overfitting. With this measure, we examine
                 the performance of one type of overfitting-avoidance
                 design frequently used in financial applications of GP.
                 Based on the simulation results run with the software
                 Simple GP, we find that this design is not effective in
                 avoiding overfitting. Furthermore, within the range of
                 search intensity typically considered by these
                 applications, we find that underfitting, instead of
                 overfitting, is the more prevalent problem. This
                 problem becomes more serious when the data is generated
                 by a process that has a high degree of algorithmic
                 complexity. This paper, therefore, casts doubt on the
                 conclusions made by those early applications regarding
                 the poor performance of GP, and recommends that changes
                 be made to ensure progress.",
  notes =        "EuroGP'2003 held in conjunction with EvoWorkshops

Genetic Programming entries for Shu-Heng Chen Tzu-Wen Kuo