A key step in market-basket analysis is to cluster customers into relatively homo- geneous groups according to their purchasing behavior. A large market-basket.

This paper presents Opossum, a novel similarity-based clustering approach based on constrained, weighted graph-partitioning. Opossum is particularly attuned ...

Jun 8, 2001 · This paper presents Opossum, a novel similarity-based clustering approach based on constrained, weighted graph-partitioning.

This paper presents Opossum, a novel similarity-based clustering approach based on constrained, weighted graph-partitioning. Opossum is particularly attuned ...

This paper proposes a parallelized hierarchical clustering approach on market-basket data (PH-Clustering), which is implemented using MPI and adopts a ...

A Scalable Approach to Balanced,. High-dimensional Clustering of Market-baskets. Alexander Strehl and Joydeep Ghosh. The University of Texas at Austin,. Austin ...

A scalable approach to balanced, high-dimensional clustering of market-baskets. A Strehl, J Ghosh. International Conference on High-Performance Computing, 525 ...

A scalable approach to balanced, high-dimensional clustering of market-baskets. In Proc. High Performance Computing (HiPC 2000), Bangalore, volume 1970 of ...

Relationship-Based Clustering and Visualization for High-Dimensional ... A Scalable Approach to Balanced, High-Dimensional Clustering of Market-Baskets.

Partitional, model-based clustering algorithms are viewed as an iterative two-step optimization process—iterative model re-estimation and sample re-assignment.