Predicting student failure at school using genetic programming and different data mining approaches with high dimensional and imbalanced data

Created by W.Langdon from gp-bibliography.bib Revision:1.3963

@Article{Marquez-Vera:2013:AI,
  author =       "Carlos Marquez-Vera and Alberto Cano and 
                 Cristobal Romero and Sebastian Ventura",
  title =        "Predicting student failure at school using genetic
                 programming and different data mining approaches with
                 high dimensional and imbalanced data",
  journal =      "Applied Intelligence",
  year =         "2013",
  volume =       "38",
  number =       "3",
  pages =        "315--330",
  month =        apr,
  keywords =     "genetic algorithms, genetic programming, educational
                 data mining, Predicting student performance,
                 Classification, Educational data mining, Student
                 failure, Grammar-based genetic programming",
  language =     "English",
  publisher =    "Springer",
  ISSN =         "0924-669X",
  DOI =          "doi:10.1007/s10489-012-0374-8",
  size =         "16 pages",
  abstract =     "Predicting student failure at school has become a
                 difficult challenge due to both the high number of
                 factors that can affect the low performance of students
                 and the imbalanced nature of these types of datasets.
                 In this paper, a genetic programming algorithm and
                 different data mining approaches are proposed for
                 solving these problems using real data about 670 high
                 school students from Zacatecas, Mexico. Firstly, we
                 select the best attributes in order to resolve the
                 problem of high dimensionality. Then, rebalancing of
                 data and cost sensitive classification have been
                 applied in order to resolve the problem of classifying
                 imbalanced data. We also propose to use a genetic
                 programming model versus different white box techniques
                 in order to obtain both more comprehensible and
                 accuracy classification rules. The outcomes of each
                 approach are shown and compared in order to select the
                 best to improve classification accuracy, specifically
                 with regard to which students might fail.",
  notes =        "Also known as \cite{Marquez:2013:AI}",
}

Genetic Programming entries for Carlos Marquez-Vera Alberto Cano Rojas Cristobal Romero Morales Sebastian Ventura

Citations