Contextualized poverty targeting with multimodal spatial data and machine learning in Brazzaville, Congo
Bibliographic Data
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.
Capability approach · Data collection · Field (mathematics) · Human welfare · Leverage (statistics) · Poverty · Urbanization · Welfare · Geographic Information Systems Studies · Human Mobility and Location-Based Analysis · Impact of Light on Environment and Health
Using publicly available satellite imagery and deep learning to understand economic well-being in Africa
Reliability and Inter-rater Reliability in Qualitative Research
Using luminosity data as a proxy for economic statistics
Cross‐validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure
Targeting the Poor
Combining satellite imagery and machine learning to predict poverty
Predicting poverty and wealth from mobile phone metadata
Targeting in Practice
A multidimensional approach to measuring vulnerability to poverty among refugee populations
Effects of a single cash transfer on school re-enrollment during Covid-19 among vulnerable adolescent girls in Kenya
Sensing urban poverty
Towards a scalable and transferable approach to map deprived areas using Sentinel-2 images and machine learning
From twitter to GDP
Measuring urban poverty using multi-source data and a random forest algorithm
High-resolution comprehensive regional development mapping using multisource geographic data
Urban poverty maps - From characterising deprivation using geo-spatial data to capturing deprivation from space
Proxy Means Testing Vulnerability to Measurement Errors
How to Target Households in Adaptive Social Protection Systems? Evidence from Humanitarian and Development Approaches in Niger
Targeting Social Safety Nets
A Class of Decomposable Poverty Measures
Counting and multidimensional poverty measurement
Community-Based Targeting Mechanisms for Social Safety Nets
The Jamaican food stamps programme
Mapping community development aid
Who is Vouching for the Input Voucher? Decentralized Targeting and Elite Capture in Tanzania
Reaching the Poor
How accurate is a poverty map based on remote sensing data? An application to Malawi
Program targeting with machine learning and mobile phone data
A poor means test? Econometric targeting in Africa
Transforming Freetown’
Predicting Multidimensional Poverty with Machine Learning Algorithms
Multidimensional Targeting
| Unique citing works | 1 |
|---|---|
| Citations per year | 1 |
| Citation span | 2026 - 2026 (1) |
| Citation velocity | current |
| Highly cited | No |
| Citation types | Neutral: 1 |