Conceptual modeling for classification mining in data warehouses

  • Authors:
  • Jose Zubcoff;Juan Trujillo

  • Affiliations:
  • Departamento de Ciencias del Mar y Biología Aplicada., Universidad de Alicante, Spain;Departamento de Lenguajes y Sistemas Informáticos., Universidad de Alicante, Spain

  • Venue:
  • DaWaK'06 Proceedings of the 8th international conference on Data Warehousing and Knowledge Discovery
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

Classification is a data mining (DM) technique that generates classes allowing to predict and describe the behavior of a variable based on the characteristics of a dataset. Frequently, DM analysts need to classify large amounts of data using many attributes. Thus, data warehouses (DW) can play an important role in the DM process, because they can easily manage huge quantities of data. There are two approaches used to model mining techniques: the Common Warehouse Model (CWM) and the Predictive Model Markup Language (PMML), both focused on metadata interchanging and sharing, respectively. These standards do not take advantage of the underlying semantic rich multidimensional (MD) model which could save development time and cost. In this paper, we present a conceptual model for Classification and a UML profile that allows the design of Classification on MD models. Our goal is to facilitate the design of these mining models in a DW context by employing an expressive conceptual model that can be used on top of a MD model. Finally, using the designed profile, we implement a case study in a standard database system and show the results.