Abstract
Every year LLDIKTI XI Kalimantan provides scholarships to universities under its auspices. Which Uniska has received scholarships since 2015-2018 as many as 152 bidik misi students for new students. Which is usually selected using manual steps with the help of human power. From the selection process there are problems, namely human factors. Therefore we need a computational process that supports the selection process. Then the SVM (Support Vector Machine) method is used for the classification process and the TOPSIS (Technique For Order Preference By Similarity To Ideal Solution) method is used to give a priority ranking of scholarship. The average speed of the entire process in the selection system and recommendations for the acceptance of the UNISKA Bidik Misi scholarship with the implementation of the SVM and TOPSIS methods using testing from a comparison ratio of 19.12 seconds, the fastest time is 14.40 and the longest time is 23.58. The accuracy of the selection and recommendation of acceptance of the UNISKA Bidik Misi scholarship using the training data comparison ratio and 90%: 10% data testing has an average accuracy of 85.53% and testing based on the best parameters of the SVM sequential training process is λ (Lambda) = 0.1 , constant γ (gamma) = 0.05, e = 0.0001, Maximum Iteration = 1000, ratio of 90%: 10% and value of d = 2, C (Complexity) = 1. So that the best accuracy is 100% and the average accuracy the best is 93.63%. Keywords: Selection, UNISKA MAB, SVM, TOPSIS, MCDM.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.