Mining Association Rules of Simple Conjunctive Queries

Abstract

We present an algorithm for mining association rules in arbitrary relational databases. We define association rules over a simple, but appealing subclass of conjunctive queries, and show that many interesting patterns can be found. We propose an efficient algorithm and a database-oriented implementation in SQL, together with several promising and convincing experimental results.

Discovery and Application of Functional Dependencies in Conjunctive Query Mining

“…Recently, we have considered association rule mining on arbitrary relational databases by combining pairs of queries which could reveal interesting properties in the database [8,13]. Intuitively, we pose two queries on the database such that one query is more specific than the other (w.r.t.…”

“…The Conqueror algorithm recently developed by Goethals et al [8] has shown to discover interesting association rules over a simple, but appealing subclass of conjunctive queries, called simple conjunctive queries. Furthermore, the algorithm had an efficient database-oriented implementation in SQL.…”

“…Clearly, the combination of the approaches in [13] and [8] would resolve the issues posed, i.e., mining non redundant simple conjunctive queries (thus including arbitrary joins), given a collection of functional dependencies over the relations of an arbitrary relational database. This is one major contribution of this paper.…”

“…We present our algorithm Conqueror + in Section 3, combining the two approaches [8,13], and in Section 4, we report experiments, showing that Conqueror + clearly outperforms Conqueror. We conclude in Section 6.…”

“…As in [8], the queries of interest in our approach, are conjunctive projection-selectionjoin queries whose joins are expressed using a conjunction of selection conditions of the form R i .A = R j .A . We note that by doing so, all possible equi-joins can be considered, which would not the case using the universal relation associated to the given database.…”