Using Artificial Intelligence/Machine Learning to Evaluate the Distribution of Community Development Aid Across Myanmar

Abstract

Achieving global poverty alleviation goals requires a systematic allocation of resources, particularly at the subnational level. However, assessing the pro-poor nature of development efforts is challenging without community-level poverty data. In the context of Myanmar, our study presents granular methods to estimate poverty and predict aid distribution based on village-specific attributes. We evaluate three poverty estimation methods, leveraging daytime and nighttime satellite imagery. Daytime image features, when processed with Convolutional Neural Networks, provide the most precise poverty estimates. Using this refined poverty metric, we deploy machine learning techniques to predict the block grant size each village receives for community development. Findings show that while impoverished villages tend to receive more grant aid per capita, wealth is not a primary factor. Instead, village capacity and state/ethnicity attributes hold more sway. The study highlights the need for an increased poverty-centric approach in community-based interventions and calls for more transparent aid allocation practice.

Keywords: community development, poverty measures, satellite images, development aid, Myanmar, world bank