Track: Data Analytics
Abstract
In addressing poverty, proper poverty alleviation programs must be identified. Analyzing the multidimensional aspects of poverty will lead to data-driven decision making. This study aims to analyze poverty conditions in a community in the Philippines using data mining and clustering algorithm. The model resulted in clusters described in this paper as Stable, Critical, and At-Risk clusters. Among the clusters, the Critical cluster has the highest incidents of poor conditions. In the cluster analysis, poverty alleviation programs where the household clusters should be prioritized were suggested based on the poor conditions in each cluster. The clusters analysis is intended to provide insights for use in the community’s planning and program implementation.