Discriminative clustering for market segmentation
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Standard
Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining. New York: Association for Computing Machinery, Inc, 2012. p. 417-425.
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - CHAP
T1 - Discriminative clustering for market segmentation
AU - Haider, Peter
AU - Chiarandini, Luca
AU - Brefeld, Ulf
N1 - Conference code: 18
PY - 2012
Y1 - 2012
N2 - We study discriminative clustering for market segmentation tasks. The underlying problem setting resembles discriminative clustering, however, existing approaches focus on the prediction of univariate cluster labels. By contrast, market segments encode complex (future) behavior of the individuals which cannot be represented by a single variable. In this paper, we generalize discriminative clustering to structured and complex output variables that can be represented as graphical models. We devise two novel methods to jointly learn the classifier and the clustering using alternating optimization and collapsed inference, respectively. The two approaches jointly learn a discriminative segmentation of the input space and a generative output prediction model for each segment. We evaluate our methods on segmenting user navigation sequences from Yahoo! News. The proposed collapsed algorithm is observed to outperform baseline approaches such as mixture of experts. We showcase exemplary projections of the resulting segments to display the interpretability of the solutions.
AB - We study discriminative clustering for market segmentation tasks. The underlying problem setting resembles discriminative clustering, however, existing approaches focus on the prediction of univariate cluster labels. By contrast, market segments encode complex (future) behavior of the individuals which cannot be represented by a single variable. In this paper, we generalize discriminative clustering to structured and complex output variables that can be represented as graphical models. We devise two novel methods to jointly learn the classifier and the clustering using alternating optimization and collapsed inference, respectively. The two approaches jointly learn a discriminative segmentation of the input space and a generative output prediction model for each segment. We evaluate our methods on segmenting user navigation sequences from Yahoo! News. The proposed collapsed algorithm is observed to outperform baseline approaches such as mixture of experts. We showcase exemplary projections of the resulting segments to display the interpretability of the solutions.
KW - Informatics
KW - Alternating optimizations
KW - Discriminative clustering
KW - GraphicaL model
KW - Input space
KW - Interpretability
KW - Market segment
KW - Market segmentation
KW - Mixture of experts
KW - Novel methods
KW - Output variables
KW - Prediction model
KW - Single variable
KW - Univariate
KW - User navigation
KW - Business informatics
UR - http://www.scopus.com/inward/record.url?scp=84866039328&partnerID=8YFLogxK
U2 - 10.1145/2339530.2339600
DO - 10.1145/2339530.2339600
M3 - Article in conference proceedings
AN - SCOPUS:84866039328
SN - 978-1-4503-1462-6
SP - 417
EP - 425
BT - Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining
PB - Association for Computing Machinery, Inc
CY - New York
T2 - 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD-2012
Y2 - 12 August 2012 through 16 August 2012
ER -