International Journal of Computer Applications (0975 – 8887) Volume 42– No.16, March 2012 26 New Dropout Prediction for Intelligent System Md.Sarwar kamal Lecturer Computer Science and Engineering BGC Trust University, Bangladesh Chondanaish, Chittagong. Linkon Chowdhury Lecturer Computer Science and Engineering BGC Trust University Bangladesh Chandanaish, Chittagong. Sonia Farhana Nimmy Lecturer Computer Science and Engineering BGC Trust University Bangladesh Chandanaish, Chittagong. ABSTRACT The main purpose of this research is to develop a dynamic dropout prediction model for universities, institutes and colleges. In this work, we first identify dependent and independent variables and dropping year to classify the successful from unsuccessful students. Then we have classify the data using Support Vector Machines(SVM).SVM helped the data set to be properly design and manipulated . The main purpose of applying this identification is to design a Knowledge Base which is sometimes known as joint probability distribution .The concepts of propositional logic helped to build the knowledge Base. Bayes theorem will perform the prediction by collecting the information from knowledge Base. Here we have considered most important factors to classify the successful students over unsuccessful students are gender, financial condition and dropping year. We also consider the socio-demographic variables such as age, gender, ethnicity, education, work status, and disability and study environment that may in-flounce persistence or dropout of students at university level Keywords: Intelligent System, Dynamic dropout Prediction, Joint Probability Distribution, Bayes Theorem Dependent ad Independent variables, Propositional Logic, Knowledge Base,MATHLAB,SVM. 1. INRODUCTION Increasing student retention or persistence is a long-term goal in all academic institutions. The consequences of student attrition are significant for students, academic and administrative staff. The importance of this issue for students is obvious: school leavers are more likely to earn less than those who graduated. Since one of the criteria for government funding in the tertiary education environment in Chittagong University is the level of retention rate and academic are under pressure to come up with most vulnerable students to low student retention at all institutions of higher education are the first-year students, who are at greatest risk of dropping out in the first term or semester of study or not completing their program /degree on time. Therefore, most retention studies address the retention of first-year students. Consequently, the early identification of vulnerable students who are prone to drop their courses is crucial for the success of any retention strategy. This would allow educational institutions to undertake timely [1] and pro-active measures. Once identified, these „at-risk‟ students can be targeted with academic and administrative support to increase their chance of staying on the course. The background characteristics such as academic and socio- demographic variables [2] (age, sex, ethnic and financial aid) have been identified in retention literature as potential predictor variables of dropout. At the time of enrolment in the Computer Science and Engineering (CSE), University of Chittagong, the only information. i.e. variables we have about students are those contained in their enrolment forms. The question we are trying to address in this paper is whether we can use the enrolment data alone to predict study outcome for newly enrolled student. The main objective of this work [2] is to explore factors that may impact the study outcome in the Technical course at the Computer science & Engineering. The Technical course is a core course for those majoring in IT and for most students an entry point, i.e. the first choice they are taking with the CSE. This issue have not been examined so far for CSE and this paper attempts to fill the gap. More specifically the enrolment data have used to achieve the following objectives: 1. Build a knowledge Base for Student information. 2. Build models for early prediction of study outcome using the student enrolment data. 3. Present results, which can be easily understood by the users (students and academic staff). 2. COLLECTED STATISTICALDATA As part of the data-understanding phase we carried out the data on the table 1 and table 2. The Table 2 reports the results. Based on the results shown majority of Information Systems students are female (over 38%). However, percentage of female students who successfully complete the course are higher (41%) which suggests that female students are more likely to [3] pass the course than their male counterpart. When it comes to age over 26% of students are above 24. This age group is also more likely to fail the course because their percentage of students who failed the course in this age group (11.9%) is higher than their overall participation in the student population (26.2%). Statistical data on 42 students: Table 1: Total Outcomes Pass 29 Fail 13 Table 2: Descriptive statistics (percentage) – Study outcome (42 students) Variable Domain Name Count Total Pass Fail Gender Male 26 61.9 58.6 69.2 Female 16 38.1 41.4 30.8 Age Group >24 11 26.2 20.7 11.9 <=24 31 73.8 79.3 61.5