Rank biserial stochastic feature embed bivariate kernelized regressive bootstrap aggregative classifier for school student dropout prediction

Early and accurately predicting the students' dropout enables schools to recognize the students based on available educational data. The early student dropout prediction is a major concern of education administrators. The existing classification techniques were unable to handle the early stage accurate performance of student dropout prediction with maximum accuracy and minimum time. In order to resolve the issue, a novel technique called rank biserial Otsuka–Ochiai stochastic embedded feature selection based bivariate kernelized regressive bootstrap aggregative classifier (RBOOSEFS‐BKBAC) is motivated to perform student dropout prediction. The aim of the designing RBOOSEFS‐BKBAC is to improve student dropout accuracy and minimal time consumption. Initially, the data preprocessing is to perform the data normalization, data cleaning, and duplicate data removal. Next, rank biserial correlation is used for discovering the correlated features. Followed by, Otsuka–Ochiai stochastic neighbor embedded feature selection is carried out to select significant features. Finally, bivariate kernelized regressive bootstrap aggregative classification technique is to perform classification with help of weak classifier. By using Bucklin voting scheme, the classification outcomes are obtained for increasing prediction accuracy as well as minimizing error. Experimental evaluation is performed by using Student‐Drop‐India2016 dataset with different metrics such as prediction accuracy, precision, recall, F‐measure, as well as time. The result of proposed RBOOSEFS‐BKBAC technique is provided that the higher prediction accuracy by 5% and lesser the prediction time by 15%, as compared to the state‐of‐the‐art methods.