Absolute Percent Error Based Fitness Functions for Evolving Forecast Models

Created by W.Langdon from gp-bibliography.bib Revision:1.8010

@InProceedings{DBLP:conf/flairs/NovobilskiK01,

• author = "Andy Novobilski and Farhad A. Kamangar",
• title = "Absolute Percent Error Based Fitness Functions for Evolving Forecast Models",
• booktitle = "Proceedings of the Fourteenth International Florida Artificial Intelligence Research Society Conference",
• year = "2001",
• editor = "Ingrid Russell and John F. Kolen",
• pages = "591--595",
• address = "Key West, Florida, USA",
• month = may # " 21-23",
• publisher = "AAAI Press",
• bibsource = "DBLP, http://dblp.uni-trier.de",
• keywords = "genetic algorithms, genetic programming, Bayesian Networks, datamining",
• ISBN = "1-57735-133-9",
• URL = "http://www.aaai.org/Papers/FLAIRS/2001/FLAIRS01-113.pdf",
• size = "5 pages",
• abstract = "One aspect of evolutionary computing as a method of data mining, is its intrinsic ability to drive model selection according to a mixed set of criteria. Based on natural selection, evolutionary computing uses evaluation of candidate solutions according to a fitness criteria that might or might not share the exact same implementation as the metric used to measure the performance of the selected solution. This paper presents the results of using four different fitness functions to evolve naive Bayesian networks based on a combination of Mean Absolute Percent Error and Worst Absolute Percent Error values for individual population members. In addition to the error measurements from both the training and forecast evaluations, data is presented that shows APE for individual members during the forecast generation and evaluation phase",
• notes = "FLAIRS 2001 Conference http://www.aaai.org/Press/Proceedings/flairs01.php",

}

Genetic Programming entries for Andrew J Novobilski Farhad A Kamangar

Citations