Multiple Imputation for Missing Data Using Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.4524

  author =       "Cao Truong Tran and Mengjie Zhang and Peter Andreae",
  title =        "Multiple Imputation for Missing Data Using Genetic
  booktitle =    "GECCO '15: Proceedings of the 2015 Annual Conference
                 on Genetic and Evolutionary Computation",
  year =         "2015",
  editor =       "Sara Silva and Anna I Esparcia-Alcazar and 
                 Manuel Lopez-Ibanez and Sanaz Mostaghim and Jon Timmis and 
                 Christine Zarges and Luis Correia and Terence Soule and 
                 Mario Giacobini and Ryan Urbanowicz and 
                 Youhei Akimoto and Tobias Glasmachers and 
                 Francisco {Fernandez de Vega} and Amy Hoover and Pedro Larranaga and 
                 Marta Soto and Carlos Cotta and Francisco B. Pereira and 
                 Julia Handl and Jan Koutnik and Antonio Gaspar-Cunha and 
                 Heike Trautmann and Jean-Baptiste Mouret and 
                 Sebastian Risi and Ernesto Costa and Oliver Schuetze and 
                 Krzysztof Krawiec and Alberto Moraglio and 
                 Julian F. Miller and Pawel Widera and Stefano Cagnoni and 
                 JJ Merelo and Emma Hart and Leonardo Trujillo and 
                 Marouane Kessentini and Gabriela Ochoa and Francisco Chicano and 
                 Carola Doerr",
  isbn13 =       "978-1-4503-3472-3",
  pages =        "583--590",
  keywords =     "genetic algorithms, genetic programming, Evolutionary
                 Machine Learning",
  month =        "11-15 " # jul,
  organisation = "SIGEVO",
  address =      "Madrid, Spain",
  URL =          "",
  DOI =          "doi:10.1145/2739480.2754665",
  publisher =    "ACM",
  publisher_address = "New York, NY, USA",
  abstract =     "Missing values are a common problem in many real world
                 databases. Inadequate handing of missing data can lead
                 to serious problems in data analysis. A common way to
                 cope with this problem is to use imputation methods to
                 fill missing values with plausible values. This paper
                 proposes GPMI, a multiple imputation method that uses
                 genetic programming as a regression method to estimate
                 missing values. Experiments on eight datasets with six
                 levels of missing values compare GPMI with seven other
                 popular and advanced imputation methods on two
                 measures: the prediction accuracy and the
                 classification accuracy. The results show that, in most
                 cases, GPMI not only achieves better prediction
                 accuracy, but also better classification accuracy than
                 the other imputation methods.",
  notes =        "Also known as \cite{2754665} GECCO-2015 A joint
                 meeting of the twenty fourth international conference
                 on genetic algorithms (ICGA-2015) and the twentith
                 annual genetic programming conference (GP-2015)",

Genetic Programming entries for Cao Truong Tran Mengjie Zhang Peter Andreae