Explaining Unemployment Rates with Symbolic Regression

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

@InCollection{Truscott:2013:GPTP,
  author =       "Philip Truscott and Michael F. Korns",
  title =        "Explaining Unemployment Rates with Symbolic
                 Regression",
  booktitle =    "Genetic Programming Theory and Practice XI",
  year =         "2013",
  series =       "Genetic and Evolutionary Computation",
  editor =       "Rick Riolo and Jason H. Moore and Mark Kotanchek",
  publisher =    "Springer",
  chapter =      "7",
  pages =        "119--135",
  address =      "Ann Arbor, USA",
  month =        "9-11 " # may,
  keywords =     "genetic algorithms, genetic programming, Abstract
                 expression grammars, Symbolic regression, Non-linear
                 regression",
  isbn13 =       "978-1-4939-0374-0",
  DOI =          "doi:10.1007/978-1-4939-0375-7_7",
  abstract =     "Much of the research on the accuracy of symbolic
                 regression (SR) has focused on artificially constructed
                 search problems where there is zero noise in the data.
                 Such problems admit of exact solutions but cannot tell
                 us how accurate the search process is in a noisy real
                 world domain. To explore this question symbolic
                 regression is applied here to an area of research which
                 has been well-travelled by regression modellers: the
                 prediction of unemployment rates. A respected dataset
                 was selected, the CEP-OECD Labor Market Institutions
                 Database, to provide a testing environment for a
                 variety of searches. Metrics of success for this paper
                 went beyond the normal yardsticks of statistical
                 significance to demand plausibility. Here it is assumed
                 that a plausible model must be able to predict
                 unemployment rates out of the sample period for six
                 future years: this metric is referred to as the out of
                 sample R-squared. We conclude that the two packages
                 tested, Eureqa and ARC, can produce models that go
                 beyond the power of traditional stepwise regression.
                 ARC, in particular, is able to replicate the format of
                 published economic research because ARC contains a high
                 level Regression Query Language (RQL). This research
                 produced a number of models that are consistent with
                 published economic research, have in sample R-squared
                 values over 0.80, no negative unemployment rates, and
                 out of sample R-squared values above 0.45. It is argued
                 that SR offers significant new advantages to social
                 science researchers.",
  notes =        "http://cscs.umich.edu/gptp-workshops/

                 Part of \cite{Riolo:2013:GPTP} published after the
                 workshop in 2013",
}

Genetic Programming entries for Philip D Truscott Michael Korns

Citations