Abstract
The classical problem of association pattern mining is defined in the context of supermarket data containing sets of items bought by customers, which are referred to as transactions. The goal is to determine associations between groups of items bought by customers, which can intuitively be viewed as k-way correlations between items. The most popular model for association pattern mining uses the frequencies of sets of items as the quantification of the level of association.
“The pattern of the prodigal is: rebellion, ruin, repentance,
reconciliation, restoration. ”—Edwin Louis Cole
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
This rule was derived in some early publications on supermarket data. No assertion is made here about the likelihood of such a rule appearing in an arbitrary supermarket data set.
- 2.
Strictly speaking, Monet is the name of the vertical database, on top of which this (unnamed) algorithm was built.
- 3.
Variations of these strategies are actually used in some implementations of these methods. We stress that the simplified versions are not optimized for efficiency but are provided for clarity.
- 4.
An ad hoc pruning optimization in FP-growth terminates the recursion when all nodes in the FP-Tree lie on a single path. This pruning optimization reduces the number of successful candidate tests but not the number of failed candidate tests. Failed candidate tests often dominate successful candidate tests in real data sets.
- 5.
FP-growth has been presented in a separate section from enumeration tree methods only because it uses a different convention of constructing suffix-based enumeration trees. It is not necessary to distinguish “pattern growth” methods from “candidate-based” methods to meaningfully categorize various frequent pattern mining methods. Enumeration tree methods are best categorized on the basis of their (i) tree exploration strategy, (ii) projection-based reuse properties, and (iii) relevant data structures.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Aggarwal, C. (2015). Association Pattern Mining. In: Data Mining. Springer, Cham. https://doi.org/10.1007/978-3-319-14142-8_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-14142-8_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-14141-1
Online ISBN: 978-3-319-14142-8
eBook Packages: Computer ScienceComputer Science (R0)