查看文章

Academic orientation is a procedure which consists in helping students to succeed in their educational path and to know the ideal path. the choice, of course, allows the student to prepare for professional life and find the right path to the future. It is therefore essential to choose the sector well to avoid any pitfall and risk hazardous choices and also reorientation. There are establishments which organize orientation sessions with the students, but the number of students is very high, which pushed us to carry out an orientation system to make this service accessible by all the students and also to make the procedure very powerful orientation and in a lapse of time. Decision making related to orientation is very complicated by the fact that it is linked to several factors (prerequisite, the student's previous academic career, marks and the number of absences by subject) as the learner’s marks give us information about his abilities and the extent of his mastery of the specialization subjects. As for the student’s tendencies and desires, they appear through his keenness on these subjects, and he is not absent from them, And it is evidenced by the number of absences by subject of the learner. These data are useful, but they pose problems in storage and processing, so the solution is to use Big Data technology. In this article we used the notes and the number of student absences by subject. These data are stored in Hadoop Distributed File System (HDFS) and processed by MapReduce using Hadoop framework. We compared the classification accuracy and speed up of Neural Networks, Naive Bayes and k-nearest-neighbors classification algorithms to make the …