A Data Warehouse System for University Administration with UML Schema and Relational Decisive Approach

Abstract

Data warehouse serves as a primary component in decision making systems by relying on multidimensional models. Multidimensional models provide a business-oriented view of data to decision makers for easy analysis and navigation. The main goal of this paper is to design a hybrid methodology depending on various multidimensional models. Intricate problems on classification require a machine learning technique called Decision tree to solve the issues in decision making. Standard algorithms for decision tree suffer from their inability in processing imprecise, meaning uncertain, incomplete and imperfect data. In this paper, a new approach for decision tree is developed using an integration of relational decisive rough set theory with improved ID3 algorithm. The proposed system illustrates how the methodology can be applied to the university environment. The performance of the system is evaluated and compared with conventional rough set methodologies. The designed model shows an improvement in the quality of conceptual schema and addresses the issues related to computational overhead.