Optimization of the Naïve Bayes classification method using the adaboost algorithm in the status of KIP college scholarship acceptance

The sustainable development goals are a global development agenda to achieve 17 goals, one of which is to improve quality education.To support education equality and improve the quality of education in Indonesia for all people, the Indonesian government provides funding assistance for education costs in each region for people who are underprivileged but still have potential and achievement.One of the scholarships provided by the government is a scholarship to enter college, namely the KIP Lecture scholarship.The data in this research was obtained from the Untan Academic and Student Affairs Administration Bureau.The method used in the research is the Nave Bayes classification method with the optimization of the AdaBoost algorithm.The data used in this research is the data of KIP Lecture scholarship acceptance at Tanjungpura University in 2022.This study uses secondary data obtained by retrieving scholarship data from the Bureau of Academic Administration and Student Affairs (BAK) Untan.The attributes used for classification consist of one dependent variable, namely the graduation status of the KIP Lecture scholarship at Tanjungpura University in 2022, and consist of six independent attributes consisting of Gender ( 1 ), Faculty ( 2 ), Father's Income ( 3 ), Mother's Income ( 4 ), Number of Dependents ( 5 ), and College Entrance Path.This research is conducted by calculating the probabilistic value of each independent attribute in the classification.Classification is determined by calculating prior and posterior probability values.After that, weighting was carried out to optimize performance using the AdaBoost algorithm, the ensemble method.The accuracy value resulting from the Nave Bayes classification is 62.96%.Then when continued with the AdaBoost algorithm, the accuracy increased to 71.56%.From the accuracy results obtained, it can be concluded that the AdaBoost algorithm is relatively good for optimizing the Nave Bayes classification method.