Data Mining for Inventory Item Selection with Cross-Selling Considerations

  • Authors:
  • Raymond Chi-Wing Wong;Ada Wai-Chee Fu;Ke Wang

  • Affiliations:
  • Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China;Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China;Department of Computer Science, Simon Fraser University, Canada

  • Venue:
  • Data Mining and Knowledge Discovery
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Association rule mining, studied for over ten years in the literature of data mining, aims to help enterprises with sophisticated decision making, but the resulting rules typically cannot be directly applied and require further processing. In this paper, we propose a method for actionable recommendations from itemset analysis and investigate an application of the concepts of association rules--maximal-profit item selection with cross-selling effect (MPIS). This problem is about choosing a subset of items which can give the maximal profit with the consideration of cross-selling effect. A simple approach to this problem is shown to be NP-hard. A new approach is proposed with consideration of the loss rule--a rule similar to the association rule--to model the cross-selling effect. We show that MPIS can be approximated by a quadratic programming problem. We also propose a greedy approach and a genetic algorithm to deal with this problem. Experiments are conducted, which show that our proposed approaches are highly effective and efficient.