Research On The Evaluation Method Of Student Financial Aid Based On SVM

The purpose of this study is to thoroughly carry out “The Notice on Enhancing and Regulating the Identifications of Impoverished Students” which was issued by the Office of the Ministry of Education.A Support Vector Machine was employed in this study to investigate the methods of evaluating university students' financial aids.A certain percentage of students were randomly selected from one university,whose library access and loans records,card consumption records,dormitory access records,and mark rankings from September in 2013 to July in 2014 were obtained.The behavioural data was analyzed by MATLAB to explore the students' real consumption,economic situation and behaviours at university.Through the analysis of the correlation between the factors and students' financial aids,the related model of the frequency of library access and loans records,consumptions,night out and mark rankings were trained and obtained.The model was used to predict the distribution of students' financial aids from September in 2014 to July in 2015,which provided the lists of impoverished students for the university.The prediction through these behaviours could find out the students of“pseudo-poverty”,so that the accurate subsidies could be achieved and every impoverished student could gain the help from the university.