Selecting the right objective measure for association analysis

623 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Introduction to arules — Mining Association Rules and Frequent Item Sets (2006, neutral): “…(Brin et al., 1997) Hyper-lift and hyper-confidence (Hahsler, Hornik, and Reutterer, 2005b) Leverage (Piatetsky-Shapiro, 1991) Improvement (Bayardo, Agrawal, and Gunopulos, 2000) Several measures from Tan, Kumar, and Srivastava (2004) (e.g., cosine, Gini index, φcoefficient, odds ratio)”
Data Mining for Web Personalization (2007, methodology): “Additional metrics have been proposed in literature that aim to quantify the interestingness of a rule [97, 123, 136], however support and conﬁdence as these are the most commonly used metrics when using association and sequence based approaches to personalization.”
Data mining for discrimination discovery (2010, methodology): “Technically, we measured discrimination through generalizations and variants of lift, a measure of the significance of an association rule [Tan et al. 2004].”
Beyond Accuracy, F-Score and ROC: A Family of Discriminant Measures for Performance Evaluation (2006, background): “Refer to ( Tan, Kumar, & Srivastava 2004 ) for an overview of the measures of support, confi dence, correlation, interest, and their key properties and to (Salzberg 1999) and (Motulsky 1995) for a discussion of when these measures are applicable.”