Mining association rules with respect to support and anti-support : experimental results
[ 1 ] Instytut Informatyki (II), Wydział Informatyki i Zarządzania, Politechnika Poznańska | [ P ] employee
2007
paper
english
- association rules
- induction
- support
- anti–support
- confirmation
- confidence
- Pareto–optimal border
EN Evaluating the interestingness of rules or trees is a challenging problem of knowledge discovery and data mining. In recent studies, the use of two interestingness measures at the same time was prevailing. Mining of Pareto-optimal borders according to support and confidence, or support and anti-support are examples of that approach. Here, we consider induction of “if..., then...” association rules with a fixed conclusion. We investigate ways to limit the set of rules non–dominated wrt support and confidence or support and anti-support, to a subset of truly interesting rules. Analytically, and through experiments, we show that both of the considered sets can be easily reduced by using the valuable semantics of confirmation measures.
534 - 542