Application of Naive Bayes Model, SVM and Deep Learning Predicting

Abstract

The college hopes that every semester students are able to pay tuition properly and smoothly. The hope is that the institution will be able to  maintain  monthly  cash  flow so  that  its  operational  and maintenance costs can be met. Therefore, this study was conducted to predict and fulfill the institution's cash-in from the method of paying tuition fees either by cash, installments, or sometimes late payments every semester. In predicting the method of paying tuition fees, using student  profile data (name,  name,  study program)  and achievement index  every  semester  for  5  semesters  passed  and  the  method  of payment  (cash,  installments,  and  late--cash  or  installments).  Using the Naive Bayes (NB) method, Support Vector Machine (SVM), and Deep Learning, this study aims to forecast tuition costs. The Classification Prediction Model with Naive Bayes, SVM, and Deep Learning produces Confusion Matrix Performance NB with an Accuracy of 91.49%, Confusion Matrix Performance SVM with an Accuracy of 85.11%, and Confusion Matrix Performance Deep Learning with an Accuracy of 89.36%, according to the research findings.

Keywords—Payments, Algorithm, Performance