Three Approaches to Deal with Tests for Inconsistent Decision Tables - Comparative Study

We present three approaches to deal with tests (super-reducts) for inconsistent decision tables. In such tables, we have groups of rows with equal values of conditional attributes and different decisions (values of the decision attribute). Instead of a group of equal rows, we consider one row given by values of conditional attributes and we attach to this row: (i) the set of all decisions for rows from the group (many-valued decisions approach); (ii) the most common decision for rows from the group (the most common decision approach); and (iii) unique code of the set of all decisions for rows from the group (generalized decision approach). For many-valued decisions approach, we consider the problem of finding an arbitrary decision from the set of decisions. For the most common decision approach, we consider the problem of finding the most common decision from the set of decisions. For generalized decision approach, we consider the problem of finding all decisions from the set of decisions. We present experimental results connected with the cardinality of tests and comparative study for the considered approaches.