Skip to main content

Measuring and Mapping Poverty and Wealth with Passively-Collected Mobile Phone Data

Accurate and timely estimates of population characteristics are a critical input to social science research and policy. In industrialized economies, novel sources of passively-collected data are enabling new approaches to population modeling and measurement. In developing countries, however, fewer sources of such .big data. exist. The notable exception is the mobile phone, which now has roughly 90% global penetration.

In this paper, we show that an individual.s past history of phone use can be used to accurately infer his or her socioeconomic status. Combining a large database of mobile phone communication records with short follow-up surveys with 900 mobile phone subscribers, we find that a rich set of behavioral metrics derived from the phone data are highly predictive of the self-reported attributes of individual survey respondents. Using models trained on this sample of 900, we then predict the socioeconomic attributes of the entire population of several million mobile phone subscribers in a small country. These individual predictions can be geographically aggregated into maps that correspond very closely to official government statistics (R2=0.86), or used to impute the characteristics of micro-regions that are much smaller than the most fine-grained administrative units of the country. In resource-constrained environments where censuses and household surveys are rare, this creates an option for gathering timely information on population demographics at a tiny fraction of the cost of traditional methods.