This chapter is concerned with a special form of Association Rule Mining known as Market Basket Analysis, the most common application of which is to relate the purchases made by the customers in a shop. An approach to finding rules of this kind, with support and confidence measures above specified thresholds, is described. This is based on the idea of supported itemsets. The Apriori algorithm for finding supported itemsets is described in detail. Further rule interestingness measures, lift and leverage, which can be used to reduce the number of rules generated are introduced.
CITATION STYLE
Bramer, M. (2013). Association Rule Mining II (pp. 253–269). https://doi.org/10.1007/978-1-4471-4884-5_17
Mendeley helps you to discover research relevant for your work.