Högskolan i Skövde

his.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Genetic rule extraction optimizing brier score
School of Business and Informatics, University of Borås, Borås, Sweden.
School of Business and Informatics, University of Borås, Borås, Sweden.
Högskolan i Skövde, Institutionen för kommunikation och information. Högskolan i Skövde, Forskningscentrum för Informationsteknologi.
2010 (engelsk)Inngår i: Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10 / [ed] Pelikan, Martin & Branke, Jürgen, New York: Association for Computing Machinery (ACM), 2010, s. 1007-1014Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

Most highly accurate predictive modeling techniques produce opaque models. When comprehensible models are required, rule extraction is sometimes used to generate a transparent model, based on the opaque. Naturally, the extracted model should be as similar as possible to the opaque. This criterion, called fidelity, is therefore a key part of the optimization function in most rule extracting algorithms. To the best of our knowledge, all existing rule extraction algorithms targeting fidelity use 0/1 fidelity, i.e., maximize the number of identical classifications. In this paper, we suggest and evaluate a rule extraction algorithm utilizing a more informed fidelity criterion. More specifically, the novel algorithm, which is based on genetic programming, minimizes the difference in probability estimates between the extracted and the opaque models, by using the generalized Brier score as fitness function. Experimental results from 26 UCI data sets show that the suggested algorithm obtained considerably higher accuracy and significantly better AUC than both the exact same rule extraction algorithm maximizing 0/1 fidelity, and the standard tree inducer J48. Somewhat surprisingly, rule extraction using the more informed fidelity metric normally resulted in less complex models, making sure that the improved predictive performance was not achieved on the expense of comprehensibility. Copyright 2010 ACM.

sted, utgiver, år, opplag, sider
New York: Association for Computing Machinery (ACM), 2010. s. 1007-1014
Emneord [en]
Brier score, Genetic programming, Rule extraction, Complex model, Data sets, Extracting algorithm, Fitness functions, Key parts, Novel algorithm, Optimization function, Predictive modeling, Predictive performance, Probability estimate, Rule extraction algorithms, Algorithms, Function evaluation, Optimization, Trees (mathematics)
HSV kategori
Forskningsprogram
Teknik
Identifikatorer
URN: urn:nbn:se:his:diva-7191DOI: 10.1145/1830483.1830668Scopus ID: 2-s2.0-77955913724ISBN: 978-1-4503-0072-8 OAI: oai:DiVA.org:his-7191DiVA, id: diva2:604426
Konferanse
12th Annual Genetic and Evolutionary Computation Conference, GECCO-2010, 7 July 2010 through 11 July 2010, Portland, OR
Merknad

Sponsors: Assoc. Comput. Mach., Spec. Interest Group Genet.; Evol. Comput. (ACM SIGEVO)

Tilgjengelig fra: 2013-02-11 Laget: 2013-02-11 Sist oppdatert: 2018-01-11bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopushttp://dl.acm.org/citation.cfm?doid=1830483.1830668

Person

Niklasson, Lars

Søk i DiVA

Av forfatter/redaktør
Niklasson, Lars
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric

doi
isbn
urn-nbn
Totalt: 500 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf