An Automated University Admission Recommender System for Secondary School Students
Simon Fong and Robert P. Biuk-Aghai neural network approach, an improved recommendation output can be achieved. The remainder of this paper is organized as follows. Section II discusses the problem of student recommendation in more detail. Section III then presents the design of our recommender system, RSAU (Recommender System of Admission to University), and Section IV evaluates the performance of our system. Section V discusses the decision rules used by RSAU. Finally, Section VI makes conclusions. II. RECOMMENDATION PROBLEM The choice of a university that is suitable for a given secondary school graduate can be a difficult decision to make. Reputation of the university, perceived difficulty of the degree program, distance from home, tuition and living costs, student’s areas of academic strength as well as actual scores achieved are just some of the factors that may be considered by a student graduating from secondary school. Likewise, the university has its own set of admission criteria, mainly based on academic standard of the student to be admitted, but possibly also including others, such as minority and gender representation, local vs. domestic vs. overseas student proportion, and others. Choosing the most suitable among the many thousands of candidates that apply to a university every year is not a trivial matter. Some universities avoid many of these issues through a simple unified admission process, such as pre-defined secondary school completion scores required for admission. This approach, however, does not always result in the most suitable candidates reaching the university “best” for them. Moreover, many accepted candidates end up not taking up the offer extended to them, resulting in wasted administrative effort on the part of the university. Most importantly, however, it
References: [1] J. C. Garcia and A. I. Zanfrillo, Data Mining Application to Decision-Making Processes in University Management, INFOCOMP Journal of Computer Science, volume 6, no.1 pp.57-65, 2007. J. Luan, Data Mining Application in Higher Education, SPSS Executive Report, 2002. J. Luan, Data Mining as Driven by Knowledge Management in Higher Education-Persistence Clustering And Prediction, Keynote speech at the University of California-San Francisco 's SPSS Public Roadshow, 2001. H. Jiawei and K. Micheline, Data Mining: Concepts and Techniques, Simon Fraser University, Morgan Kaufmann publishers, 2001. S. Fong, Y. W. Si, R. P. Biuk-Aghai, "Applying a Hybrid Model of Neural Network and Decision Tree Classifier for Predicting University Admission”, The 7th International Conference on Information, Communications and Signal Processing (ICICS 2009), Submitted for publication. W. C. Lou, " A Hybrid Model of Tree Classifier and Neural Network for University Admission Recommender System," Master of Science Thesis, University of Macau, Faculty of Science and Technology, 2008. S. Alexander, M. Clark, K. Loose, “Case studies in admissions to and early performance in computer science degrees”, In ITiCSEWGR ' 03: Working group reports from ITiCSE on Innovation and technology in computer science education, ACM Press, pp.137-147 Fig. 10. A fragment of the importance decision rules for recommendation (with a high value of confidence). When the decision rules are translated into a more comprehensive language, the rules do give some insights about the students and the university admissions. Some samples are derived in our experiments in the context of secondary schools in Macau. It is believed, however, RSAU would work equally well with data from students of secondary schools from other countries. Scores are still an important factor for qualifying students to universities, especially for Mathematics and English courses. When students’ score of Mathematics and English are higher than 80%, almost all of them will be attended to universities. Whereas, when students’ score of courses Mathematics and English are lower than 60%, they are likely to give up furthering their studies in universities. Female students, who are born in Macau are likely to enter local universities in Macau. The students who are major in Science class with youngest ages have higher probabilities of being recommended for direct admission to universities in mainland China. A large number of mature aged students have fewer chances to be recommended for direct admission to universities. In general, students who did not repeat in their last few years of secondary school study, have a good probability of admission to universities in mainland China or University in Macau. If the study status of a female student is not of any advancement and the average score is below 70%, the probability of giving up university study is higher than a male student. The female students from Guangdong have higher probabilities of giving up university study than those who are from Fujian, China. The female students who are major in Arts, and are born in China, have higher probabilities of recommendation to universities in China than those born in Macau. [2] [3] [4] [5] [6] [7] 42