Optimization of Human Development Index in Indonesia Using Decision Tree C4.5, Support Vector Machine Algorithm, K-Nearest Neighbors, Naïve Bayes, and Extreme Gradient Boosting

The Human Development Index (HDI) is a measure of human development achievement based on quality of life indicators such as Life Expectancy (LE), Mean Years of Schooling (MYS), Expected Years of Schooling (EYS), and Adjusted Per Capita Expenditure (AECE). HDI describes how people access development outcomes through income, health, and education. The determination of development programs implemented by local governments must be based on district/city priorities based on their HDI categories and must be right on target. Therefore, a decision system is needed that can accurately determine the HDI category in each district/city in Indonesia, using machine learning models such as Decision Tree C4.5, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Naïve Bayes, and Extreme Gradient Boosting (XGBoost). Machine learning models will be used to classify the HDI in Indonesia in 2022 and determine the performance of the most optimal model in classification. This research uses the CRISP-DM method with secondary data from the Central Statistics Agency (BPS) as much as 548 data. The analysis results show that the Decision Tree C4.5 models have an accuracy of 0.86, KNN of 0.95, Naïve Bayes of 0.90, XGBoost of 0.93, and SVM provides the most optimal results with an accuracy of 0.97. UHH, RLS, and HLS variables significantly influence changes in HDI values in Indonesian regions based on the Chi-square, Pearson Correlation, Spearman, and Kendal test results.