K-Means – Resilient Backpropagation Neural Network in Predicting Poverty Levels

In solving economic problems, the government has implemented several development policies. However, this policy is considered to be too centered on big cities. So, through research it hoped that can provide an overview related regional groups fall into poorer category so also accelerated policies are oriented towards improving economy of residents in area. This study aims determine results classifying district/city poverty levels Indonesia as a basis for classification predictions and classify based influencing factors. The method used K-Means Clustering using depth index severity variables, then proceed with Backpropagation Neural Network (BNN) algorithm GRDP, per capita expenditure, human index, mean years schooling. obtained there 42 districts/cities belong cluster 1 where region value higher than 472 2. Furthermore, response variables BNN. accuracy model very high, which equal 98.06, feasible rate prediction used.