Student Data Analysis with RapidMiner
Jovica Krstevski
1
, Dragan Mihajlov
2
, Ivan Chorbev
3
1
Innovaworks. ul.Partizanski Odredi 73, MK-1000 Skopje, Republic of Macedonia
jovicakrstev@yahoo.com
2,3
Faculty of Electrical Engineering and Information Technologies, PO Box 574,
Skopje, Republic of Macedonia
{dragan, ivan}@feit.ukim.edu.mk
Abstract. The aim of this paper is to propose a methodology for modeling and
implementing algorithms over data from student management systems with
RapidMiner. RapidMiner is an environment for business analytics, predictive
analytics, data mining, text mining, and machine learning. Traditional
educational systems collect a lot of data about students. The collected data can
be used to extract information and experiences. The extracted information can
help school managers prepare better curriculum and manage the schools in an
informed manner. Teachers can have advanced information about student
progress and the potential weaknesses in courses. In this paper we describe how
tools like RapidMiner can be used to extract information from raw student data.
We have used student data from the Macedonian educational system, compared
different algorithms and chose the most appropriate for the given model.
Keywords: Student Analysis, Academic Analytic, Educational Data Mining,
RapidMiner.
1 Introduction
We are witnesses of how modern world education plays a significant role in
people’s lives. The growing need for an educated workforce in the society requires
education to be a leader in the reform of the economy. During the last decades an
increasing number of educational organizations store their data in electronic format
and the amount of stored information is increasing each day. In order to analyze
collected data one needs a process where the data will be inspected, cleaned,
transformed, and modeled. From the analysis one can extract information, propose
conclusions and support decision making. Data analysis can be found in science,
social and business domains. It has different approaches and includes versatile
techniques with different names. This process in the educational area is called
Educational Data Mining (EDM) [5], which converts student raw data from
educational systems to information to help the educational process.
ICT Innovations 2011 Web Proceedings ISSN 1857-7288 19
L. Kocarev (Editor): ICT Innovations 2011, Web Proceedings, ISSN 1857-7288
© ICT ACT – http://ictinnovations.org, Skopje, 2012