Educational data mining to reduce dropout rate of students using classification

International Conference on Big Data Analysis and Data Mining

May 04-05, 2015 Kentucky, USA

Khawar Shakeel and Naveed Anwar Butt

Scientific Tracks Abstracts: J Comput Sci Syst Biol

Abstract :

The Educational Data Mining is currently a growing research area with having emphasis on logical methods for especially educationally linked data in order to improve the system and quality of higher education institutions. Overall the Educational Data Mining aims to interact with the relevant information from any educational data and further transform into a systematic and understandable knowledge for the sake of decision making. Classification techniques can be highly helpful in predicting student?s performance. The current study aimed to evaluate student performance by using different Decision Tree and Bayes algorithms. The results of the study affirm the usefulness and functionality of the prediction model and these facilitate the institutions to identify weak students having enrollment status at risk and student needing further help. The study found highest accuracy in Naive Bayes among four algorithms as above ninety percent. Naive Bayes was concluded to be the best algorithm and execution of proposed model confirmed the claim.

Biography :

Khawar Shakeel has completed his Master of Science from Hafiz Hayat Campus, University of Gujrat. Currently he is working as a Computer Programmer/Data Base Administrator in a leading university of Pakistan (University of Gujrat) for last 3 years.