P.Senthil Vadivu et al., International Journal of Advances in Computer Science and Technology, 3(5), May 2014, 318 - 324 318 Survey on Students’ Academic Failure and Dropout using Data Mining Techniques P.Senthil Vadivu 1 , D.Bharathi 2 1 Head and Associate Professor, Department of computer Applications, Hindustan college of Arts and Science, India, sowju_sashi@rediffmail.com 2 Research Scholar, Hindustan college of Arts and Science, India, bharathi196@gmail.com ABSTRACT Educational data mining is in the habit of learn the data available in the field of education and show up the hidden knowledge from it. Classification methods like decision trees, machine learning, rule mining, etc can be applied on the educational data for forecasting the student’s behavior, performance of them in examination etc. This prediction will well helpful for tutors to classify the weak students and help them to score improved marks. The classification approach is applied on student’s internal assessment data to predict their performance in the final exam. The result of the classification categorized the number of students who are to be expected to fail or pass. The outcome result is given to the tutor and steps were taken to improve the performance of the students who were predicted as fail in the examination. After the statement of the results in the final examination the marks acquired by the students are provide into the system and the results were investigated. The proportional analysis results states that the prediction has helped the weaker students to improve and brought out betterment in the result. The algorithm is also analyzed by duplicating the same data and the result of the duplication brings no much change in predicting the student’s outcome. The goal of this survey is presented the several data mining techniques in determining of student failure. This article provides a review of the available literature on Educational Data mining, Classification method and different feature selection techniques that we should apply on Student dataset. Keywords: Educational data mining, Classification techniques, Attribute selection techniques and Clustering techniques. 1. INTRODUCTION An educational system has large number of educational data. The educational data is possibly students’ data, teachers’ data, alumni data, resource data etc. Educational data mining is used to find out the patterns in this data for decision-making. There are two types of education system: 1) Traditional Education system: In this system there is direct contact between the students and the teacher. Students’ record containing the information such as attendance, grades or marks which is get from the examination that may be kept manually or digitally. Students’ performance is the measure of this information. 2) Web based learning system: It is also known as e-learning. It is attractive more admired as the students can gain knowledge from any place without any time restriction. In a web based system, several data about the students are automatically together with the help of logs. Educational data mining can response number of queries from the prototypes attained from student data such as 1) Who are the students at risk? 2) What are the chances of placement of student? ISSN 2320 - 2602 Volume 3, No.5, May 2014 International Journal of Advances in Computer Science and Technology Available Online at http://warse.org/pdfs/2014/ijacst03352014.pdf