Evaluation System For International Student Application Using Nearest-neighbor Case Retrieval Technique

Abstract

Important decisions are made based not on the information-rich data stored in databases but rather on a decision maker’s intuition because the decision maker does not have the tools to extract the valuable knowledge embedded in the vast amount of data. Data mining tools perform data analysis and may uncover important data patterns, contributing greatly to business strategies, knowledge bases, and scientific and educational and medical research. Among the variety of knowledge based approaches to decision support, Case-Based Reasoning (CBR)is increasingly emerging as one of the most promising approaches for complex data rich domains such as education, health and business. The principal method used in the memory is case-based reasoning method which can provide solving new problem by adapting previous solution to similar problems. CBR’s cyclical process is used to support enhancing a process’s performance of an expert. This method retrieves the appropriate cases from a large set of cases. If the similar between a new case and the retrieved case are very high, the previous solution to that case is returned to users. This system is tested on international student data at AIT’s school of engineering and technology. International student data who applied for AIT’s school of engineering and technology and who had permission to enter the university are used as old cases. Unknown cases are matched with old cases. If unknown cases and old cases are the same, the system displays accept. Nearest-neighbor case retrieval technique (NNR) is used to find the similarity measure for the cases which are not found exactly in old cases. If the similarity measure is over 0.5, the system displays accept. If not, the system displays reject.