Modeling Student Performance in Higher Education Using Data Mining

Identifying students’ behavior in university is a great concern to the higher education managements (Kumar and Uma, Eur J Sci Res 34(4):526–534). This chapter proposes a new educational technology system for use in Knowledge Discovery Processes (KDP). We

  • PDF / 681,901 Bytes
  • 20 Pages / 439.37 x 666.142 pts Page_size
  • 76 Downloads / 208 Views

DOWNLOAD

REPORT


Modeling Student Performance in Higher Education Using Data Mining Huseyin Guruler and Ayhan Istanbullu

Abstract Identifying students’ behavior in university is a great concern to the higher education managements (Kumar and Uma, Eur J Sci Res 34(4):526–534). This chapter proposes a new educational technology system for use in Knowledge Discovery Processes (KDP). We introduce the educational data mining (EDM) software and present the outcome of a test on university data to explore the factors having an impact on the success of the students based on student profiling. In our software system all the tasks involved in the KDP are realized together. The advantage of this approach is to have access to all the functionalities of the Structured Query Language (SQL) Server and the Analysis Services through a single developed software item, which is specific to the needs of a higher education institution. This model (Guruler et al., Comput Educ 55(1):247–254) aims to help educational organizations to better understand the KDPs, and provides a roadmap to follow while executing whole knowledge projects, which are nontrivial, involve multiple stages, possibly several iterations.



Keywords Educational data mining Educational technology system and architectures Student relationship management Knowledge discovery software Decision tree







H. Guruler (&) Department of Information Systems Engineering, Technology Faculty, Mugla Sitki Kocman University, 48000 Kötekli, Mugla, Turkey e-mail: [email protected] A. Istanbullu Department of Computer Engineering, Engineering and Architecture Faculty, Balikesir University, 10145 Cagis, Balikesir, Turkey e-mail: [email protected]

A. Peña-Ayala (ed.), Educational Data Mining, Studies in Computational Intelligence 524, DOI: 10.1007/978-3-319-02738-8_4,  Springer International Publishing Switzerland 2014

105

106

H. Guruler and A. Istanbullu

Abbereviations CM DBMS DM DT DTS EDM GPA KDD KDP MDAC MDT OLAP PDCA SKDS SRM SQL

Correlation matrices Database management system Data mining Decision tree Data transformation services Educational data mining Grade point average Knowledge discovery in databases Knowledge discovery process Microsoft data access components Microsoft decision tree On-line analytical processing Plan-do-check-act Student knowledge discovery software Student relationship management Structured query language

4.1 Introduction Appropriate decisions can be made by effectively analyzing and managing the growing volume of data. Gaining information from business data started with data collection in the 1960s; this type of data collection answered questions related to the past. In the 1980s, with the development of relational databases, data access methods were introduced. In the 1990s, data warehousing and decision support systems were created based on multi-dimensional databases and On-line Analytical Processing (OLAP). Today, data mining (DM) produces a particular enumeration of patterns in data. This should be understandable and usable by the business end user