Classification of Indonesian Government Budget Appropriations or Outlays for Research and Development (GBAORD) Using Decision Tree and Naive Bayes

摘要

Indonesian Government Budget Appropriations or Outlays for Research and Development (GBAORD) is one of component from Indonesian Gross Expenditure on Research and Development (GERD). Calculation of GBAORD are made by classifying each government expenditure budget. Classification is done manually so that there are frequent inconsistencies. This study proposed an automated classification using decision tree and Naive bayes algorithm to handle problem in previous method. The result of study have conclusion that an automated classification using Naive bayes is more accurate than using decision tree. The highest average accuracy score given by Naive Bayes model in this experiment is 98.462 while decision tree gives about 90.236. This can be related to the number of features involved in classification process. Naive Bayes uses most of the features in data while decision tree only uses one feature. Although decision tree model only uses one feature, the accuracy score produced by the model is considered as high.