The Self-Evolving Logic of Financial Claim Prices

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

@InProceedings{RePEc:sce:scecf7:102,
  author =       "Thomas H. Noe",
  title =        "The Self-Evolving Logic of Financial Claim Prices",
  booktitle =    "Third International Conference on Computing in
                 Economics and Finance",
  year =         "1997",
  editor =       "Kenneth L. Judd",
  address =      "Stanford, California, USA",
  month =        jun # " 30 - " # jul # " 2",
  organisation = "Society of Computational Economics",
  keywords =     "genetic algorithms, genetic programming",
  URL =          "http://bucky.stanford.edu/cef97/abstracts/noe.html",
  URL =          "http://ideas.repec.org/p/sce/scecf7/102.html",
  abstract =     "we will price financial claims by allowing option
                 pricing programs to evolve trough time via combining
                 with each other, mutating randomly, and reproducing at
                 rates based on the pressure of evolutionary selection.
                 The specific technique we employ is Genetic
                 Programming, an optimisation technique based on the
                 principles of natural selection. Compared to the
                 traditional arbitrage-based approach, this technique is
                 useful when the underlying asset dynamics are unknown
                 or when the pricing equations are too complicated to
                 solve analytically. Compared to other established
                 data-driven option pricing techniques such as neural
                 networks, implied binomial trees, etc., genetic
                 programming has the advantage of not restricting the
                 structure of the pricing formulas, formulae themselves
                 evolve rather than simply the parameters of a single
                 formula. Our analysis is preliminary. However, by
                 showing that genetic programming can recover
                 Black-Sholes formula from a fairly small data sample,
                 we hope to validate the ability of genetic programming
                 approaches to consistently and efficiently estimate
                 option prices, at least in structurally simple
                 environments. Future research will apply genetic
                 programming approach to more intractable problems in
                 derivative asset pricing.",
  notes =        "CEF 1997 number 102 http://bucky.stanford.edu/cef97/",
}

Genetic Programming entries for Thomas H Noe

Citations