Data Mining Ontologies
The e-LICO data mining ontologies serve a number of different objectives. The first is to support planning of the knowledge discovery process and construction of workflows for a user task. This is pursued through the Data Mining Work Flow (DMWF) Ontology.
The second objective is to support algorithm, model and workflow selection for data mining tasks that require search in the space of possible methods and models. The third objective is to support meta-mining, or learning from past experience to improve data mining performance. The Data Mining Optimization (DMOP) Ontology has been developed in pursuit of these last two objectives.