- author = "Mark E. Kotanchek and Ekaterina Y. Vladislavleva and Guido F. Smits",
- title = "Symbolic Regression via GP as a Discovery Engine: Insights on Outliers and Prototypes",
- booktitle = "Genetic Programming Theory and Practice {VII}",
- year = "2009",
- editor = "Rick L. Riolo and Una-May O'Reilly and Trent McConaghy",
- series = "Genetic and Evolutionary Computation",
- address = "Ann Arbor",
- month = "14-16 " # may,
- publisher = "Springer",
- chapter = "4",
- pages = "55--72",
- keywords = "genetic algorithms, genetic programming, symbolic regression, data modeling, system identification, research assistant, discovery engine, outlier detection, outliers, prototypes, data balancing",
- isbn13 = "978-1-4419-1653-2",
-
DOI = "
doi:10.1007/978-1-4419-1626-6_4",
-
abstract = "In this chapter we illustrate a framework based on
symbolic regression to generate and sharpen the
questions about the nature of the data-generating
system and provide additional context and understanding
based on the multi-variate numeric data. We emphasize
the necessity to perform data modeling in a global
approach iteratively applying data analysis &
adaptation, model building, and problem reduction
procedures. We demonstrate it for the problem of
detecting outliers and extracting significant features
from the CountryData
{http://reference.wolfram.com/mathematica/ref/CountryData.html}
-- a data set of economic, political, social and
geographic data collected. We present two complementary
ways of extracting outliers from the data -the
content-based and the model-based approach. The
content-based approach studies the geometrical
structure of the multi-variate data, and uses
data-balancing algorithms to sort the data records in
the order of decreasing typicalness, and identifies the
outliers as the least typical records before the
modeling is applied to a data set. The model-based
outlier detection approach uses symbolic regression via
Pareto genetic programming to identify records which
are systematically under- or over-predicted by diverse
ensembles of (thousands of) global non-linear symbolic
regression models.
Both approaches applied to the CountryData produce insights into outlier vs. prototypes division among world countries and about driving economic properties predicting gross domestic product (GDP) per capita.",
- notes = "part of \cite{Riolo:2009:GPTP}",
