Mutual Information Based Clustering of Market Basket Data for Profiling Users

e-Finance Lab Discussion Paper No. 13/2007

Posted: 19 May 2008

See all articles by Bartholomäus Ende

Bartholomäus Ende

Goethe University Frankfurt Faculty of Economics and Business Administration

Rüdiger S. Brause

Goethe University Frankfurt - Dept. of Computer Science and Mathematics

Multiple version iconThere are 2 versions of this paper

Abstract

Attraction and commercial success of web sites depend heavily on the additional values visitors may find. Here, individual, automatically obtained and maintained user profiles are the key for user satisfaction. This contribution shows for the example of a cooking information site how user profiles might be obtained using category information provided by cooking recipes. It is shown that metrical distance functions and standard clustering procedures lead to erroneous results. Instead, we propose a new mutual information based clustering approach and outline its implications for the example of user profiling.

Suggested Citation

Ende, Bartholomäus and Brause, Rüdiger S., Mutual Information Based Clustering of Market Basket Data for Profiling Users. e-Finance Lab Discussion Paper No. 13/2007, Available at SSRN: https://ssrn.com/abstract=1133395

Bartholomäus Ende (Contact Author)

Goethe University Frankfurt Faculty of Economics and Business Administration ( email )

Grueneburgplatz 1
Frankfurt am Main, 60323
Germany

HOME PAGE: http://www.efinancelab.de/no_cache/team/?user_wiwipubs_pi2[showUid]=653

Rüdiger S. Brause

Goethe University Frankfurt - Dept. of Computer Science and Mathematics ( email )

Grüneburgplatz 1
Frankfurt am Main, 60323
Germany

Do you have negative results from your research you’d like to share?

Paper statistics

Abstract Views
472
PlumX Metrics