Prediction of Technical Education Student Performance using ARM

Abstract

From the last few years, statistical techniques are utilized to analyze the Performance of Students in Academics by considering some parameters. In Present days because of state and central governments schemes, technical education is having admissions from more rural area students. In the same manner urban development also having influences in technical education admissions. This paper focuses implementing association rule mining to identify powerful rules from the existing data, which is used to discover the importance to the student performance related to the instructive environment where they will study. We have recognized the association among dissimilar attributes of educational background i.e., college locality, college type, diverse societal groups, dissimilar courses etc., and thereby dig up powerful association rules. For the administrators of technical education, from the existing data the unidentified rules are extracted and analyzed to take better decisions for growth of the institutes. These rules are also useful for a right perceptive of fire instructive location aids in course structure and other required up gradations to get better students' educational performance. This paper focuses on association rule mining to identify powerful rules from the existing data of higher education institutes which will be used to know the success patterns of students of different colleges based on societal groups. Additionally we have analyzed processed the available data to find the pattern of support for these rules from time to time.