top of page
Big Data & Aid Targeting in Myanmar
Project Description
In Myanmar, “Using Artificial Intelligence/machine learning to evaluate the distribution of community development aid across Myanmar (2025)” examines how community development projects are distributed spatially across local communities. Specifically, this research seeks to understand which communities are more likely to receive large amounts of development aid based on their poverty levels and other development characteristics. Toward this aim, “Mapping community development aid: Spatial analysis in Myanmar (2023)” develops granular poverty measures drawn from satellite imagery that are consistently available in the country. The paper creates aid density measures and visualizes aid hotspots. The concept of community-centered development was introduced in her paper “Two models of community-centered development in Myanmar (2020)”. These studies were among the earliest to compare the predictive power of nightlights with geospatially interpolated wealth in predicting aid amount per village.
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, examine targeting, and predict aid distribution based on village-specific attributes. We evaluate multiple poverty estimation methods, leveraging both daytime and nighttime satellite imagery along with geofeatures. Daytime image features, when processed with Convolutional Neural Networks, provide the most accurate poverty estimates. Using this refined poverty metric, we evaluate the targeting error and deploy machine learning (ML) techniques to predict the block grant size each village receives for community development. Findings show that a majority of beneficiary villages have predicted wealth above the median, resulting in high targeting errors. 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 in Myanmar with potential implications for other conflict-prone countries.
Citation
Jung, W., Ghadimi, S., Ntarlagiannis, D., & Kim, A. H. (2025). Using Artificial Intelligence/machine learning to evaluate the distribution of community development aid across Myanmar. Socio-Economic Planning Sciences.
ASSOCIATED RESEARCH:
Mapping Community Development Aid: Spatial Analysis in Myanmar (2023)
Using Computer Vision & Deep Learning to Predict Poverty and Aid in Data-Sparse Contexts (2020)
Findings in this study suggest that nuances captured in nightlight luminosity can predict CLD aid density in Myanmar. Brighter nightlights are strongly correlated with higher aid density in that community. The model fit of this variable is better than other poverty-related variables.
​
Nightlight shows promise in capturing the variability of economic development in target villages and improving prediction of aid allocation.
Dr. Jung conducted analysis at the smallest geographical unit at the village level, or, at the administrative level 5. One of the measurements of this study, aid hotspots, does not depend on administrative boundaries.
​
..................................................................................................................................................................................
​
This study promotes evidence-based targeting for area-based interventions, lacking location specific and timely data. It addresses the disconnect between communities wanting to mobilize resources and development agencies identifying populations to serve. Exploring new data sources and synthesizing them with administrative and survey data at a fine-grained level extends their utility as a policy design and evaluation tool.
​
bottom of page