Main Article Content


Data mining and machine learning depend on classification which is the most essential and important task. Many experiments are performed on Student datasets using multiple classifiers and feature selection techniques. Many of them show good classification accuracy. The existing work proposes to apply data mining techniques to predict Students dropout and failure. But this work d oesn’t support the huge amount of data. It also takes more time to complete the classification process. So the time complexity is high. To improve the accuracy and reduce the time complexity, the MapReduce concept is introduced. In this work, the deadline constraint is also introduced. Based on this, an extensional MapReduce Task Scheduling algorithm for Deadline constraints (MTSD) is proposed. It allows user to specify a job’s (classification process in data mining) deadline and tries to make the job to be finished before the deadline. Finally, the proposed system has higher classification accuracy even in the big data and it also reduced the time complexity.

Article Details

How to Cite
M.Mohammed Imran, R.Swaathi, K.Vasuki, A.Manimegalai, & A.Tamil arasan. (2017). Prediction of student performance . International Journal of Intellectual Advancements and Research in Engineering Computations, 5(2), 1283–1286. Retrieved from