Utilizing feature selection in identifying predicting factors of student retention

Abstract

Student retention is an important issue faced by Philippine higher education institutions. It is a key concern that needs to be addressed for the reason that the knowledge they gain can contribute to the economic and community development of the country aside from financial stability and employability. University databases contain substantial information that can be queried for knowledge discovery that will aid the retention of students. This work aims to analyze factors associated with student's success among first-year students through feature selection. This is a critical step prior to modelling in data mining, as a way to reduce computational process and improve prediction performance. In this work, filter methods are applied on datasets queried from university database. To demonstrate the applicability of this method as a pre-processing step prior to data modelling, predictive model is built using the selected dominant features. The accuracy result jumps to 92.09%. Also, through feature selection technique, it was revealed that post-admission variables are the dominant predictors. Recognizing these factors, the university could improve their intervention programs to help students retain and succeed. This only shows that doing feature selection is an important step that should be done prior to designing any predictive model.