CCCG is a more general framework for constrained clustering, it supports two types of constraints: Must-link constraints which imply that two objects must be clustered together, and Can-not-link constraints which enforce that two objects have to be clustered in two different groups.

CCCG is based on an integer linear programming formulation of clustering problem, and hence obtains an exact solution for this problem. The clustering criterion used in CCCG is similar to that of k-means algorithm, namely to minimize the sum of squared distances from cluster centers.

The goal of constraint-based sequence mining is to find sequences of symbols that are included in a large number of input sequences and that satisfy some constraints specified by the user.

Dominance Programming is an extension of Gecode that supports the use of pair-wise order relations between solutions.

LPS (Learning from Polyhedral Sets) solves the problem of learning the definition of a class of polyhedra from sample polyhedral sets. The learned definition is expressed as a parameterized linear system. LPS is implemented in SWI-Prolog using a library for constraint logic programming over the reals.

NetQuantify is a data mining software to perform the quantification task on network data. It exploits the homophily effect observed in many social networks to quantify in a network collective behaviour, i.e., the number of users that are involved in certain type of activities, preferences, or behaviors.

Quantify is a data mining software to perform the quantification task. It constructs a quantification tree for a supervised learning to estimate the distribution across the classes in a test set from a training set of labeled individuals.