Constraint programming for itemset mining

Abstract

The relationship between constraint-based mining and constraint programming is explored by showing how the typical constraints used in pattern mining can be formulated for use in constraint programming environments. The resulting framework is surprisingly flexible and allows us to combine a wide range of mining constraints in different ways. We implement this approach in off-the-shelf constraint programming systems and evaluate it empirically. The results show that the approach is not only very expressive, but also works well on complex benchmark problems.

k-Pattern Set Mining under Constraints

“…These are the constraints that have been identified in the framework of constraint-based mining [7]. We will review some of the most important constraints for the itemset mining problem here.…”

“…Nevertheless, also in such cases the formulation as a constraint programming model provides insights that may be used for developing more heuristic declarative approaches to the kpattern set mining problem (e.g., using local search), and hence this work may contribute to the longer term vision of developing general purpose declarative data mining tools. This is similar to the constraint programming approach to mining for local patterns [7].…”

“…Constraint programming (CP) is a generic framework for solving combinatorial and optimization problems under constraints. It has been used successfully in numerous applications including constraint based mining of individual patterns [7,8]. The key power of constraint programming lies in its declarative approach towards problem solving: in constraint programming, users model a problem by specifying a set of constraints, and the CP system is responsible for solving the problem.…”

“…An important part of this work is the extension of our earlier work on constraint programming for local pattern mining [7,8] towards the mining of entire pattern sets. Our earlier work showed that appropriate constraint programming models can lead to practical solutions for computationally hard problems, in particular for the case of correlated itemset mining in [8].…”

The Top-k Frequent Closed Itemset Mining Using Top-k SAT Problem

“…Note that several data mining tasks are closely related to the itemset mining problem such as the ones of association rule mining, frequent pattern mining in sequence data, data clustering, etc. Recently, De Raedt et al in [24,25] proposed the first constraint programming (CP) based data mining framework for itemset mining. This new framework offers a declarative and flexible representation model.…”