Intelligent higher institution student selection system

Higher education institutions admission faces the need for a precise and effective method to evaluate and select the most qualified applicants to be in their institution. Currently, admission officers have to manually evaluate every applicant's data against the set of admission requirements before selecting the few successful ones. The manual process contributes many problems such as inaccurate decision resulting from human error, needs a lot of effort and is time consuming. The objectives of the paper is to identify and suggest an intelligent selection method using fuzzy system to assist higher institutions to select the most suitable applicants and also suggest suitable course based on their high school certificate result. There are two phases involved in this project. The first phase requires user to input the data which will be processed in the fuzzy inference system. If the applicant qualifies, the system will proceed to the second phase which is course suggestion phase. The result shows whether the applicant qualify and if so, will be suggested a course. This project uses Suge-no-Style Fuzzy Inference technique to select the suitable applicants. A prototype was developed and tested with thirty sample data. From the analysis, this prototype achieved 83% accuracy. As a conclusion, this technique is suitable to be applied to automatically suggest suitable applicants for intake into higher institutions.

[1]  Leibniz-Informationszentrum Wirtschaft.  Telling the truth may not pay off: an empirical study of centralised university admissions in Germany , 2007 .

[2]  P. Biró.  Higher education admission in Hungary by a “score-limit algorithm” , 2007 .

[3]  Jayanthi Ranjan,et al.  Conceptual Framework of Data Mining Process in Management Education in India: An Institutional Perspective , 2008 .

[4]  P. Haddawy,et al.  A decision support system for evaluating international student applications , 2007, 2007 37th Annual Frontiers In Education Conference - Global Engineering: Knowledge Without Borders, Opportunities Without Passports.

[5]  M. Tech,et al.  Web-Based Neural Network Model for University Undergraduate Admission Selection and Placement , 2007 .

[6]  Pengpeng Lin,et al.  A Framework for Consistency Based Feature Selection , 2009 .

[7]  Melody Y. Kiang,et al.  A comparative assessment of classification methods , 2003, Decis. Support Syst..

[8]  Dorothea Kübler,et al.  Telling the Truth May Not Pay Off : An Empirical Study of Centralized University Admissions in Germany , 2011 .

[9]  Simon Fong,et al.  An Automated University Admission Recommender System for Secondary School Students , .

[10]  R. Bhaskaran,et al.  A Study on Feature Selection Techniques in Educational Data Mining , 2009, ArXiv.

[11]  V. O. Oladokun,et al.  Predicting Students' Academic Performance using Artificial Neural Network: A Case Study of an Engineering Course. , 2008 .

[12]  F. Lievens,et al.  Admission systems to dental school in Europe: a closer look at Flanders. , 2010, European journal of dental education : official journal of the Association for Dental Education in Europe.

[13]  D. Morisky,et al.  A Longitudinal Study of the Impact of Interviews on Medical School Admissions in Taiwan , 2010, Evaluation & the health professions.

[14]  Samuel DiGangi,et al.  A Data Mining Approach for Identifying Predictors of Student Retention from Sophomore to Junior Year , 2021, Journal of Data Science.

[15]  Kevin Knight,et al.  Artificial intelligence (2. ed.) , 1991 .

[16]  Students Choosing Colleges: Understanding the Matriculation Decision at a Highly Selective Private Institution , 2010 .