Contextualized Poverty Targeting

Project Description
AI/ML models are predominantly developed in countries with georeferenced national surveys. “Contextualized Poverty Targeting Through Multimodal Spatial Data and Machine Learning in Brazzaville, Congo” demonstrates that household-level targeting can be achieved in a data deficient city without a gold standard survey. Using the case of Brazzaville, this study integrates intuitive images, social media, points of interest, connectivity, and administrative data to predict multidimensional poverty at the household level. The simulation in this study shows that a spatially augmented targeting method not only reduces targeting errors but also decreases the poverty ratio, gap, and severity. 

Abstract
Enhancing targeting accuracy in social welfare programs fosters equitable urban development. Advancements in this field harness georeferenced data and leverage AI/machine learning (ML) techniques to predict poverty and allocate aid. However, these models are predominantly developed in areas with georeferenced national surveys and are intended for geographic targeting. We demonstrate that micro, household-level targeting can be achieved in understudied cities lacking ground truth data. Using the case of Brazzaville in Congo, we integrate intuitive images, social media, points of interest, connectivity, and administrative data to predict multidimensional poverty at the household level. The simulation in this study demonstrates that ML-based targeting not only reduces targeting errors but also decreases the poverty ratio, gap, and severity. Our spatially augmented model, surpassing status quo mechanisms, can promote inclusive social welfare programs at hyper-granular levels in urban areas. Given the rapid urbanization in developing countries, this study’s data collection and fine-tuning process is relevant and applicable to other data-sparse contexts.