期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2017
卷号：5
期号：4
页码：7370
DOI：10.15680/IJIRCCE.2017.05040153
出版社：S&S Publications
摘要：In recent years, Engineering Institutes and Universities are increasing in number. This has lead toincrease in students opting for Engineering Education however there has also been increase in dropout rate. Inworldwide scenario this has increased the need to study the characteristics of students who are being admitted andstudents who are pursuing education so that the increasing dropout rate can be brought under control. Such scenariocan be due to various factors such as unsatisfactory level of learning amongst students, poor academic achievement ofstudent, lack of parent engagement, economic needs of parents, low grasping power and many more. Hence, measuresto overcome these factors must be identified, studied and implemented to control the rate of dropouts.“EducationalData Mining” describes research discipline that uses data from educational settings such as universities and collegesand develops methods to gain information and knowledge from the data. A model is proposed using Educational DataMining that would predict students who are likely to dropout from engineering education. Students’ records such asSSC and HSSC percentages, board of education in SSC and HSSC, Working Status of parents, internal and endsemester marks, attendance, performance in remedial classes and many such parameters are taken into account todevelop the model to predict whether the student is likely to dropout or fail in Engineering Education. Also parameterssuch as father’s income, student’s gender, category, and his residing place throughout the education are alsoconsidered. The predictions can aid teachers to adopt various proactive measures to deal with such students. They canplan the teaching style or methods for such students and thus control the drop-out rates in the institution.
关键词：Engineering Education; unsatisfactory level; Educational data mining; Working Status; predictions;proactive measures
