摘要
Since about 10 years ago, University of Applied Science and Technology (UAST) in Iran has admitted students in discontinuous associate degree by modular method, so that almost 100,000 students are accepted every year. Although the first aim of holding such courses was to improve scientific and skill level of employees, over time a considerable group of unemployed people have been interested to participate in these courses. According to this fact, in this paper, we mine and analyze a sample data of accepted candidates in modular 2008 and 2009 courses by using unsupervised and supervised learning paradigms. In the first step, by using unsupervised paradigm, we grouped (clustered) set of modular accepted candidates based on their student status and labeled data sets by three classes so that each class somehow shows educational and student status of modular accepted candidates. In the second step, by using supervised and unsupervised algorithms, we generated predicting models in 2008 data sets. Then, by making a comparison between performances of generated models, we selected predicting model of association rules through which some rules were extracted. Finally, this model is executed for Test set which includes accepted candidates of next course then by evaluation of results, the percentage of correctness and confidentiality of obtained results can be viewed.
Since about 10 years ago, University of Applied Science and Technology (UAST) in Iran has admitted students in discontinuous associate degree by modular method, so that almost 100,000 students are accepted every year. Although the first aim of holding such courses was to improve scientific and skill level of employees, over time a considerable group of unemployed people have been interested to participate in these courses. According to this fact, in this paper, we mine and analyze a sample data of accepted candidates in modular 2008 and 2009 courses by using unsupervised and supervised learning paradigms. In the first step, by using unsupervised paradigm, we grouped (clustered) set of modular accepted candidates based on their student status and labeled data sets by three classes so that each class somehow shows educational and student status of modular accepted candidates. In the second step, by using supervised and unsupervised algorithms, we generated predicting models in 2008 data sets. Then, by making a comparison between performances of generated models, we selected predicting model of association rules through which some rules were extracted. Finally, this model is executed for Test set which includes accepted candidates of next course then by evaluation of results, the percentage of correctness and confidentiality of obtained results can be viewed.
