Contextualized poverty targeting with multimodal spatial data and machine learning in Brazzaville, Congo

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 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 simulations in this study demonstrate that ML-based targeting would not only reduce targeting errors but would also decrease 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. • Achieve household poverty prediction in an understudied city lacking ground truth. • Feature-engineer and integrate intuitive image, social media, POIs, and phone data. • Develop machine-learning-based targeting by comparing and fine-tuning algorithms. • Outperform existing targeting methods and the global poverty prediction model. • Show substantial poverty reduction impact through policy simulation.