Towards an Ontology of Data Mining Investigations

Motivated by the need for unification of the domain of data mining and the demand for formalized representation of outcomes of data mining investigations, we address the task of constructing an ontology of data mining. In this paper we present an updated version of the OntoDM ontology, that is based on a recent proposal of a general framework for data mining and it is aligned with the ontology of biomedical investigations (OBI) . The ontology aims at describing and formalizing entities from the domain of data mining and knowledge discovery. It includes definitions of basic data mining entities (e.g., datatype, dataset, data mining task, data mining algorithm etc.) and allows extensions with more complex data mining entities (e.g. constraints, data mining scenarios and data mining experiments). Unlike most existing approaches to constructing ontologies of data mining, OntoDM is compliant to best practices in engineering ontologies that describe scientific investigations (e.g., OBI ) ...

• Type: Conference
• Year: 2009
• Where: DIS
• Authors: Pance Panov, Larisa N. Soldatova, Saso Dzeroski
• Keywords: Data Mining, Data Mining Entities, Data Mining Investigations, DIS 2009, Theoretical Computer Science