ICTworks

Many critical decisions require accurate, quantitative data on the local distribution of wealth and poverty.

• Governments and non-profit organizations rely on such data to target humanitarian aid and design social protection systems;
• Businesses use this information to guide their marketing and investment strategies;
• These data also provide the foundation for entire fields of basic and applied social science research.

Yet reliable socioeconomic data are expensive to collect, and only half of all countries have access to adequate data on poverty. In some cases, the data that do exist are subject to political capture and censorship, and very rarely do such data allow for disaggregation beyond the largest administrative level.

The scarcity of quantitative data is thus a major impediment to policymakers and researchers interested in solutions to global poverty and inequality. Data gaps similarly hinder the broad international coalition working toward the Sustainable Development Goals, in particular toward the first goal of ending poverty in all its forms everywhere.

Constructing Accurate Poverty Maps

To address these data gaps, researchers have developed several approaches to construct poverty maps from non-traditional sources of data. These include methods from small area statistics that combine household sample surveys with comprehensive census data, and more recent use of satellite ‘night-lights’, mobile phone data, social media data, high-resolution satellite imagery, or some combination of these.

But these efforts have focused on a single continent or a select set of countries, limiting their relevance to development objectives that require a more global perspective.

In Micro-Estimates of Wealth for all Low- and Middle-Income Countries, we develop a novel approach to construct micro-regional wealth estimates, and use this method to create the first complete set of micro-estimates of the distribution of poverty and wealth across all 135 LMICs. We use this method to generate, for each of roughly 19.1 million unique 2.4km micro-regions in all global LMICs, an estimate of the average absolute wealth (in dollars) and relative wealth (relative to others in the same country) of the people living in that region.

These estimates, which are more granular and comprehensive than previous approaches, make it possible to see extremely local variation in wealth disparities. Our approach relies on “ground truth” measurements of household wealth collected through traditional f ace-to-face surveys with 1,457,315 unique households living in 66,819 villages in 56 different LMICs around the world.

These Demographic and Health Surveys (DHS), which are independently funded by the U.S. Agency for International Development, contain detailed questions about the economic circumstances of each household, and make it possible to compute a standardized indicator of the average asset-based wealth of each village.

We then use spatial markers in the survey data to link each village to a vast array of non-traditional digital data. This includes:

• high-resolution satellite imagery,
• data from mobile phone networks,
• topographic maps,
• aggregated and de-identified connectivity data from Facebook.

These data are processed using deep learning and other computational algorithms, which convert the raw data to a set of quantitative features of each village. We use these features to train a supervised machine learning model that predicts the relative wealth and absolute wealth of each all populated 2.4km grid cells in LMICs.

The estimates of wealth and poverty are quite accurate. Depending on the method used to evaluate performance, the model explains 56-70% of the actual variation in household-level wealth in LMICs. This performance compares favorably to state-of-the-art methods that focus on single countries or continents.

To provide visual intuition for the fine granularity of the wealth estimates, we show an enlargement of a region in the outskirts of Cape Town, South Africa. The satellite imagery shows the physical terrain, which juxtaposes high-density urban areas with farmland and undeveloped zones by the airport and off the main highway. We show the wealth estimates for the same region, which highlight the contrast in wealth between these neighboring area.

Accurate Poverty Maps Use Cases

We are making these micro-regional estimates of relative wealth and poverty, along with the associated confidence intervals, freely available for public use and analysis. These estimates are provided through an open and interactive data interface that allows scientists and policymakers to explore and download the data.

How might these estimates be used to guide real-world policymaking decisions?

One key application is in the targeting of social assistance and humanitarian aid. In the months following the onset of the COVID-19 pandemic, hundreds of new social protection programs were launched in LMICs, and in each case, program administrators faced difficult decisions about whom to prioritize for assistance. This is because in many LMICs, planners do not have comprehensive data on the income or consumption of individual households. The new estimates provide one potential solution.

In simulations, we find that geographic targeting using our micro-estimates allocates a higher share of benefits to the poor (and a lower share of benefits to the non-poor) than geographic targeting approaches based on recent nationally representative household survey data. This is because the micro-estimates make it possible to target smaller geographic regions than would be possible with traditional survey data – a finding that is consistent with prior work that suggests that more granular targeting can produce large gains in welfare.

• Poverty Maps for Nigeria: For instance, the most recent DHS survey in Nigeria only surveyed households in 13.8% of all Nigerian wards (the smallest administrative unit in the country); by contrast, the micro- estimates cover 100% of wards. Based on the strength of these results, the Government of Nigeria is using these estimates as the basis for social protection programs that are providing benefits to millions of poor families.
• Poverty Maps for Togo: In Togo, existing government surveys only provide poverty estimates that are representative at the regional level (of which there are only 5); we provide estimates for 9,770 distinct tiles. The Government of Togo is using these estimates to target mobile money transfers to hundreds of thousands of the country’s poorest mobile subscribers.

These examples highlight how the ML estimates can improve targeting performance even in countries with robust national statistical offices, like Nigeria and Togo. In the large number of LMICs that have not conducted a recent nationally representative household survey, these micro-estimates create an option for geographic targeting that would otherwise not exist.

The standardized procedure through which these estimates are produced may also be attractive in contexts where political economy considerations might lead to systematic misreporting of data or influence whether new data are collected at all. However, this does not imply the ML estimates are apolitical, as maps have a historical tendency to perpetuate existing relations of power.

One particular concern is that the technology used to construct these estimates may not be transparent to the average user; if not produced or validated by independent bodies, such opacity might create alternative mechanisms for manipulation and misreporting.

Poverty Maps Show Data Relevance

While our primary focus is on constructing, validating, and disseminating this new resource, the process of building this dataset produces several insights relevant to the construction of high-resolution poverty maps. For instance, we find that different sources of input data complement each other in improving predictive performance.

While prior work has focused heavily on satellite imagery, we find that models trained only on satellite data do not perform as well as models that include other input data. In particular, information on mobile connectivity is highly predictive of sub-regional wealth, with 5 of the 10 most important features in the model related to connectivity.

The global scale of our analysis also reveals intuitive patterns in the geographic generalizability of machine learning models. We find that models trained using data in one country are most accurate when applied to neighboring countries.

Models also perform better in countries when trained on countries with similar observable characteristics. And while much of the model’s performance derives from being able to differentiate between urban and rural areas, the model can differentiate variation in wealth within these regions as well.

Our hope is that these methods and maps can provide a new set of tools to study economic development and growth, guide interventions, monitor and evaluate policies, and track the elimination of poverty worldwide.

A lightly edited introduction from Micro-Estimates of Wealth for all Low- and Middle-Income Countries, by Guanghua Chi, University of California, Berkeley; Han Fang, Facebook, Inc.; Sourav Chatterjee, Facebook, Inc.; Joshua Blumenstock, University of California, Berkeley