Feature selection techniques and classification algorithms for student performance classification: a review

The process of categorizing students’ performance based on input data,encompassing demographic information and final exam results, isrecognized as student performance classification. Educational data mininghas gained traction in assessing students’ performance. However, this studyentails the need to analyze the diverse attributes of students’ informationwithin an educational institution by using data mining techniques. This studythoroughly examines both previous and current methodologies presented byresearchers, addressing two main aspects: data preprocessing andclassification algorithms applied in student performance classification. Datapreprocessing specifically delves into the exploration of feature selectiontechniques, encompassing three types of feature selection and searchmethods. These techniques aim to identify the most significant features,eliminate unnecessary ones, and reduce data dimensionality. In addition,classification algorithms play a crucial role in categorizing or predictingstudent performance. Models such as k-nearest neighbors (KNN),decision tree (DT), artificial neural networks (ANN), and linear models (LR)were scrutinized based on their performance in prior research. Ultimately,this study highlights the potential for further exploration of feature selectiontechniques like information gain, Chi-square, and sequential selection,particularly when applied to new datasets such as students’ online learningactivities, utilizing a variety of classification algorithms.