Classification of the placement success in the undergraduate placement examination according to decision trees with bagging and boosting methods

Abstract

The purpose of this study is to classify the data set which is created by taking students whoplaced to universities from 81 provinces, in accordance with Undergraduate PlacementExamination between the years 2010-2013 in Turkey, with Bagging and Boosting methodswhich are Ensemble algorithms. The data set which is used in the study was taken from thearchives of Turk-Stat. (Turkish Statistical Institute) and OSYM (Assessment, Selection andPlacement Center) and MATLAB statistical software program was used. In order to evaluateBagging and Boosting classification performances better, the success rates of the studentswere grouped into two groups. According to this, the provinces that were above the averagewere coded as 1, and the provinces below the average were coded as 0 and dependentvariables were created. The Bagging and Boosting ensemble algorithms were runaccordingly. In order to evaluate the prediction abilities of the Bagging and Boostingalgorithms, the data set was divided into training and testing. For this purpose, while the databetween 2010-2012 yearrs were used as training data, the data of the year 2013 were used astesting data. Accuracy, precision, recall and f-measure were used to demonstrate theperformance of the methods in the study. As a result, the performance in consequence of"Bagging” and “Boosting” methods were compared. According to this; it was determinedthat in all performance measure marginally “Boosting” method produced better results thanthe “Bagging” method.