Classification on Educational Performance Evaluation Dataset Using Feature Extraction Approach

Abstract

With the drastic drive in population and economy of Bangladesh, the urgency of higher education of the mass is also extending. Moreover, due to scarcity of resources, financial support and many other convoluted circumstances, for many of the university going youth, concentrating on study becomes arduous. Such phenomenon implies a repercussion on their academic result; which is absolutely not expected. In order to minimize such unwanted damages, we have carried out an investigation by surveying a number of undergraduate students of various universities of Bangladesh. Through our research, we have tried to excavate the key features which mostly contribute to the aforementioned matter. Our research primarily focuses on the features that have been extracted by the feature selection process we have implemented. Firstly, we have conducted classifier comparison on the original dataset which has provided us an insight about the distribution of the dataset. Furthermore, we have extracted out the most telling features with the help of feature importance ranking measure. Finally, we have once again carried out classifier comparison on the reduced dataset which has demonstrated better accuracy than that of the original dataset.