Microestimates of wealth for all low- and middle-income countries

Abstract

Many critical policy decisions, from strategic investments to the allocation of humanitarian aid, rely on data about the geographic distribution of wealth and poverty. Yet many poverty maps are out of date or exist only at very coarse levels of granularity. Here we develop microestimates of the relative wealth and poverty of the populated surface of all 135 low- and middle-income countries (LMICs) at 2.4 km resolution. The estimates are built by applying machine-learning algorithms to vast and heterogeneous data from satellites, mobile phone networks, and topographic maps, as well as aggregated and deidentified connectivity data from Facebook. We train and calibrate the estimates using nationally representative household survey data from 56 LMICs and then validate their accuracy using four independent sources of household survey data from 18 countries. We also provide confidence intervals for each microestimate to facilitate responsible downstream use. These estimates are provided free for public use in the hope that they enable targeted policy response to the COVID-19 pandemic, provide the foundation for insights into the causes and consequences of economic development and growth, and promote responsible policymaking in support of sustainable development.

Occupations on the map: Using a super learner algorithm to downscale labor statistics

“…Second, we aim to apply our approach to larger regions, such as South-East Asia and the world, resulting in a product that complements existing global maps with socio-economic indicators, such as population (www.worldpop.org), education (Graetz et al, 2019) and wealth (Chi et al, 2022). For a substantial number of countries, the required subnational labor statistics can be extracted from the population census, which is available by means of the IPUMS database (Minnesota Population Center, 2019).…”

“…For many other countries, only a few data points, representing Ąrst-level administrative units or broad regions, might be available. Combining the data of a large number of countries will make it possible to train machine learning models that achieve higher accuracy and that can be used to generate plausible out-of-sample predictions for countries for which no data is available (Chi et al, 2022;Nicolas et al, 2016).…”

“…To evaluate the accuracy of our model estimates at grid level, we compared the predicted occupation shares with a high-resolution (2.4 km) global wealth index map (Chi et al, 2022). The wealth index is based on a machine learning model that used satellite imagery, mobile phone networks and connectivity data from Facebook as predictors and asset information from the Demographic and Health Surveys (DHS) as target variables, covering the period 2010-2018.…”

“…This paper contributes to a rapidly expanding literature, which uses machine learning and advanced statistical models to create Ąne-scale gridded maps of socio-economic indicators. Key examples include the mapping of population (Leyk et al, 2019), educational attainment (Graetz et al, 2019), child growth (Osgood-Zimmerman et al, 2018), poverty (Pokhriyal et al, 2017) and wealth (Chi et al, 2022). Within this Ąeld, our approach resembles the work of Stevens et al (2015) and Nicolas et al (2016), who disaggregated subnational information to create gridded population and livestock maps but only applied a single type (random forest) of machine learning model.…”

The adoption of non-pharmaceutical interventions and the role of digital infrastructure during the COVID-19 Pandemic in Colombia, Ecuador, and El Salvador

“…The index, publicly released in 2021, measures the relative standard of living within countries using machine learning, de-identified connectivity data, satellite imagery, and other nontraditional data sources (more details in Ref. [68]). It is available for nearly 93 low and middle income worldwide at a very high spatial resolution (30m population density tiles).…”