Algoritma Bayesian Regulation untuk Prediksi Kemiskinan Sebagai Evaluasi Awal Mendukung Kebijakan Ekonomi Hijau

This study aims to utilize the Bayesian Regulation algorithm to predict poverty in Simalungun, Pematangsiantar, Asahan, Batu Bara, and Tebing Tinggi, as an initial step to evaluate the Green Economy policy. Poverty remains a serious issue, particularly in Pematangsiantar and Simalungun, where social inequality and limited access to basic services are prevalent. High poverty rates and limited resources present significant challenges to improving community welfare. The Green Economy policy could be a potential solution to reduce the negative environmental impact of development and enhance community well-being. This research uses secondary time-series poverty data from 2012 to 2023, obtained from the Central Bureau of Statistics of North Sumatra, based on the basic needs approach. The applied Machine Learning algorithm is Bayesian Regulation, used to predict poverty levels in these areas based on five architectural models (10-5-1, 10-10-1, 10-15-1, 10-20-1, and 10-25-1). The 10-25-1 model was selected as the best model due to its smallest MSE (error), 0.00218055780, compared to the other four models. This study aims to provide insights into the development of poverty in these regions and offer an initial evaluation of the effectiveness of the Green Economy policy. It is also expected to propose more effective policy recommendations for reducing poverty and supporting environmental sustainability, particularly in Pematangsiantar and Simalungun.