Analysing and Improving Student Performance Using Data Mining and Business Intelligence
Karan Napanda1, Sujil Shah2, Ojas Kharbe3, Sindhu Nair4
1Karan Napanda, Department of Computer, D.J. Sanghvi College of Engineering, Mumbai, Maharashtra, India.
2Sujil Shah, Department of Computer, D.J. Sanghvi College of Engineering, Mumbai, Maharashtra, India.
3Ojas Kharbe, Department of Computer, D.J. Sanghvi College of Engineering, Mumbai, Maharashtra, India.
4Prof. Sindhu Nair, Department of Computer, D.J. Sanghvi College of Engineering, Mumbai, Maharashtra,India
Manuscript received on 08 December 2015 | Revised Manuscript received on 16 December 2015 | Manuscript Published on 30 December 2015 | PP: 16-19 | Volume-5 Issue-7, December 2015 | Retrieval Number: G2240125715/2015©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Academic failures among university students have been the subject of concern in higher education community. Students drop out due to poor academic performance as early as in the first year of their university enrolment. Many interested parties’ debate and try to find reasons for this poor performance. Consequently, the ability to predict a student’s performance could be useful in many ways to stakeholders of higher education institutions. The proposed system puts forward data mining techniques used to identify the significant variables that affects and influences the performance of undergraduate students. Students’ demographic and past academic performance data are then used to study the academic pattern. The knowledge is hidden among the educational data set and it is extractable through various data mining techniques. Such knowledge can be extracted from end semester exams, talents, ethics, grasping power, involvement in extracurricular activities, mid term tests and other educational data sets. Data classification algorithms coupled with decision trees assist in such extraction which can further be analyzed to produce semantic rules to predict student’s final performance. The system utilizes semantic web technologies such as ontologies and semantic rules to enhance the quality of the educational content and the delivered learning activities to each student. This proposed system generates a type of confidence among the students and teachers. Hence, the system aims to analyse this extracted such data and mine educational data to produce graphical and statistical results which can help in the improvement of student’s performance and also give tutors an overview of the proficiency of the student’s learning abilities.
Keywords: Data Mining, ID3, Naïve Bayes, Perceptron Learning rule, Student Performance Analysis
Scope of the Article: Data Mining