Student’s performance prediction using data mining technique depending on overall academic status and environmental attributes

Abstract

In the education sector, it has been a challenging task to identify the students individually to take appropriate actions to get a very deserving outcome from them. On the other hand, a student getting higher education should have the knowledge about the market demands and where are their weaknesses. If it is possible to get some data from students’ academic record and their percepts on some factors related to academic performances those may help to understand the reasons for success and failure which would be very useful in the educational environment and student’s success rate. We collect data from students from different institutes. First, we create an online survey form to get data, and then we process them to get some valuable information. After getting those data, we visualize then analyze them from different prospects. We try to get some exact knowledge which can be crucial for students’ success or failure in an academic environment. We apply the data mining technique decision tree algorithm (j48) to develop a model that shows us the hierarchy of different attributes related to students’ academic performance and their personal behaviors that affect a students’ academic status. Then we try to get information about which attributes have positive and which attribute has a negative impact on students’ academic growth.