A Comparative Performance Analysis of Data Mining Classification Algorithms on Predicting Students’ Placement into Subject-Area Classes in Senior Secondary Schools


  • journal manager


Data mining, Cross validation, Junior and Senior Secondary Schools, Nigeria


Omoyele, T. D. and Akinola, S.O.
Department of Computer Science,
University of Ibadan, Oyo State, Nigeria
The information age has enabled many institutions to gather large volumes of data. However, the usefulness of this
data is negligible if knowledge cannot be extracted from it. Data mining attempts to answer this need. Data mining
is the process of analyzing data from different perspectives and summarizing it into useful information which can
help in decision making. A secondary school with efficient data mining approach can use the prediction model to
place junior secondary students into various class categories (Science, Arts or Commercial) in the Senior Secondary
Schools in order to improve quality of education and increase success rate. In this study, students’ scores in English,
Civic Education, Social Studies, Mathematics, Integrated Science, Fine Art, Business Studies and Introductory
Technology at the Junior Secondary Classes were obtained. Classification algorithms such as J48, IBK, JRipper
and Naïve Bayes were applied on the Junior Secondary final score data in order to determine the best class category
of students at Senior Secondary level. The result of this study shows that J48 algorithm performed well for the
prediction and can be used as a best predicting model algorithm for the type of data collected. The result of this
experiment shows that the marks obtained in the various subjects in the Junior Secondary Schools can determine the
best class category a student can be placed in the Senior Secondary School.