Machine Learning-Enhanced Geographically Weighted Regression for Spatial Evaluation of Human Development Index across Western Indonesia

Abstract

The HDI (Human Development Index) is one of the important components to measure the level of success in efforts to improve the quality of human life. The human development index is built with three dimensions, namely the longevity and health dimension, the knowledge dimension and the decent standard of living dimension. The longevity and health dimension is measured using Life expectancy at birth. The knowledge dimension is measured using expected years of schooling and average years of schooling. Meanwhile, the decent standard of living dimension is measured using Adjusted per capita expenditure. This study aims to find factors that influence HDI (Human Development Index) in Western Indonesia Region using machine learning models. The results obtained are that HDI is influenced by average years of schooling, expected years of schooling, Life expectancy at birth, and Adjusted per capita expenditure which are sorted from the most significantly influential. The model used in this study is GWR (Geographically Weighted Regression) with evaluation results including, AIC of 215.3162, AICc of 226.5107, and the accuracy level in the form of R-square of 99.38% which means this model is good to use.

Keywords

• human development index, geographically weighted regression, machine learning, western indonesia region, spatial, regression