Knowledge-based model to support decision-making when choosing between two association data mining techniques
Loading...
Date
2017
Journal Title
Journal ISSN
Volume Title
Publisher
Corporación Universitaria Lasallista
Abstract
Introduction. This paper presents the functionality
and characterization of two Data Mining (DM)
techniques, logistic regression and association rules
(Apriori Algorithm). This is done through a conceptual
model that enables to choose the appropriate data
mining project technique for obtaining knowledge
from criteria that describe the specific project to be
developed. Objective. Support decision making
when choosing the most appropriate technique for
the development of a data mining project. Materials
and methods. Association and logistic regression
techniques are characterized in this study, showing
the functionality of their algorithms. Results. The
proposed model is the input for the implementation
of a knowledge-based system that emulates a human
expert’s knowledge at the time of deciding which data
mining technique to choose against a specific problem
that relates to a data mining project. It facilitates
verification of the business processes of each one of
the techniques, and measures the correspondence
between a project’s objectives versus the components
provided by both the logistic regression and the
association rules techniques. Conclusion. Current
and historical information is available for decisionmaking
through the generated data mining models.
Data for the models are taken from Data Warehouses,
which are informational environments that provide an
integrated and total view of the organization.
Description
Keywords
Corporación Universitaria Lasallista, Minería de datos, Reglas de asociación, Regresión logística, Algoritmo apriori, Toma de decisiones
Citation
Revista Lasallista de Investigación Vol. 14 N. 2