A computational environment for mining association rules and frequent item sets in R


Type Research Project

Duration Jan. 6, 2004 - Jan. 5, 2008

  • Applied Information Technology with Focus on IT in Organization AE (Details)
  • Mathematical Methods in Statistics AE (Former organization)
  • Research Institute for Computational Methods FI (Details)

Tags

Press 'enter' for creating the tag
  • Hahsler, Michael (Former researcher) Project Head
  • Hornik, Kurt (Details) Project Head
 

Abstract (German)

Das finden von Assoziationsregeln ist eine weit verbreitetes und gut untersuchtes Verfahren
zur Auffindung von interessante Beziehungen zwischen Variablen in großen Datenbanken (z.B. Verbundeffekte in Warenkorb-Daten). Das R Paket arules wird die Infrastruktur zur Bearbeitung von Transaktionsdaten und zum Erzeugen von Assoziationsregeln zur Verfügung stellen.

<p>
Weitere Entwicklungen beinhalten:
<ul>
<li> Clusterbildung für Assoziationsregeln und Segmentierung von Transaktionsdaten (inklusive Visualisierung)
<li> Entwicklung neuer Maße für Assoziationsregeln.
<li> Entwicklung von Datengeneratoren.
</ul>


Abstract (English)

Mining frequent itemsets and association rules is a popular and well researched approach to discovering interesting relationships between variables in large databases. The R package arules will provide a basic infrastructure for creating and manipulating input data sets and for analyzing the resulting itemsets and rules.
<p>
Further developments include:
<ul>
<li> Clustering of rules and segmentation of transaction data (includes the visualization and proximity measures)
<li> Developments of new, statistical interest measures for association rules
<li> Development of generators for artificial data
</ul>

Publications

Journal article

2007 Hahsler, Michael, Hornik, Kurt. 2007. New Probabilistic Interest Measures for Association Rules. Intelligent Data Analysis 11 (5): 437-455. (Details)
  Reutterer, Thomas, Hahsler, Michael, Hornik, Kurt. 2007. Data Mining und Marketing am Beispiel der explorativen Warenkorbanalyse. Marketing. Zeitschrift für Forschung und Praxis (ZFP) 29 (3): 163-179. (Details)
2005 Hahsler, Michael, Grün, Bettina, Hornik, Kurt. 2005. arules - A computational environment for mining association rules and frequent item sets. Journal of Statistical Software 14 (15): 1-25. open access (Details)

Chapter in edited volume

2006 Hahsler, Michael, Hornik, Kurt, Reutterer, Thomas. 2006. Warenkorbanalyse mit Hilfe der Statistik-Software R. In Innovationen in Marketing und Handel, Hrsg. Schnedlitz, Peter, Buber, Renate, Reutterer, Thomas, Schuh, Arnold, Teller, Christoph, 144-163. Wien: Linde. (Details)

Contribution to conference proceedings

2007 Hahsler, Michael, Hornik, Kurt. 2007. Building on the arules infrastructure for analyzing transaction data with R. In Advances in Data Analysis, Proceedings of the 30th Annual Conference of the Gesellschaft für Klassifikation e.V., Hrsg. R. Decker and H.-J. Lenz, 449-456. Berlin: Springer. (Details)
2006 Hahsler, Michael, Hornik, Kurt, Reutterer, Thomas. 2006. Implications of probabilistic data modeling for mining association rules. In From Data and Information Analysis to Knowledge Engineering, Studies in Classification, Data Analysis, and Knowledge Organization, Hrsg. M. Spiliopoulou, R. Kruse, C. Borgelt, A. Nürnberger, and W. Gaul, 598-605. Berlin: Springer. (Details)

Paper presented at an academic conference or symposium

2006 Hahsler, Michael, Hornik, Kurt. 2006. An association rule mining infrastructure for the R data analysis toolbox. 30th Annual Conference of the German Classification Society (GfKl 2006), Berlin, Deutschland, March 8-10. (Details)