Statistical metadata in knowledge discovery

• Main Authors: Claudia Jiménez Ramírez, Maria Edith Burke, Ivonne Rodríguez Flores
• Format: Article
• Language: English
• Published: Universidad Nacional de Colombia 2017-07-01
• Series: Dyna
• Subjects: statistical metadata; knowledge discovery; knowledge management; data analytics
• Online Access: https://revistas.unal.edu.co/index.php/dyna/article/view/61417

Metadata represents the semantic schema of the data collected over the years by an organization in order to apply the business intelligence approach.  However, the metadata normally collected are not enough to facilitate knowledge discovery processes because they are conceived, primarily, for the interoperability between information systems. Research undertaken in this study confirmed the need to enrich data warehousing systems with structured meaningful metadata in order to increase the productivity and efficacy of any investigation, including data management and future business analytics. This need led us to adopt and extend the concept of “statistical metadata”. Thus, our proposed conceptual model of statistical metadata not only considers recognized standards, but also represents other additional properties. This means that our conceptual model allows increased levels of detail about the data and quality of the semantic contents.