Enhancing Financial Decision Making Using Multi-Objective Financial Genetic Programming

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

@InProceedings{Li:2006:CEC,
  author =       "Jin Li and Sope Taiwo",
  title =        "Enhancing Financial Decision Making Using
                 Multi-Objective Financial Genetic Programming",
  booktitle =    "Proceedings of the 2006 IEEE Congress on Evolutionary
                 Computation",
  year =         "2006",
  editor =       "Gary G. Yen and Lipo Wang and Piero Bonissone and 
                 Simon M. Lucas",
  pages =        "7935--7942",
  address =      "Vancouver",
  month =        "6-21 " # jul,
  publisher =    "IEEE Press",
  keywords =     "genetic algorithms, genetic programming",
  ISBN =         "0-7803-9487-9",
  URL =          "http://www.cs.bham.ac.uk/~jxl/cercialink/web/publication/MOFGP-JinSope.pdf",
  DOI =          "doi:10.1109/CEC.2006.1688575",
  size =         "8 pages",
  abstract =     "a multi-objective genetic programming based financial
                 forecasting system, MOFGP. MOFGP is built upon our
                 previous decision-making tool, FGP (Financial Genetic
                 Programming) [1]-[5]. By taking advantage of the
                 techniques of multi-objective evolutionary algorithms
                 (MOEAs), MOFGP enhances FGP in a number of ways.
                 Firstly, MOFGP is faster in obtaining the same quantity
                 of diverse forecasting models optimised with respect to
                 multiple conflicting objectives. This is attributed to
                 the inherent property of MOEAs, i.e., a set of Pareto
                 front solutions can be obtained in a single execution
                 of its algorithm. Secondly, MOFGP is friendlier and
                 simpler from the user's perspective. It is friendlier
                 because it eliminates a number of user-supplied
                 parameters previously required by FGP. Consequently, it
                 becomes simpler as the user no longer needs to have a
                 priori domain knowledge required for the proper use of
                 those parameters. Finally, compared with FGP, which
                 exploits a canonical single-objective approach to
                 tackle a multi-criterion financial forecasting problem,
                 MOFGP demonstrates the above advantages without
                 seriously sacrificing its forecasting performance,
                 although it suffers from an inadequate generalisation
                 capability over the test data in this study. Given its
                 strengths and weaknesses, MOFGP could be employed as a
                 useful starting investigative tool for financial
                 decision making.",
  notes =        "WCCI 2006 - A joint meeting of the IEEE, the EPS, and
                 the IEE.

                 IEEE Catalog Number: 06TH8846D",
}

Genetic Programming entries for Jin Li Sope Taiwo

Citations