Predicting Socioeconomic Status Using Big Data

Abstract Big data offers the potential to calculate timely estimates of the socioeconomic development of a region. Mobile telephone activity provides an enormous wealth of information that can be utilized alongside household surveys. Estimates of poverty and wealth rely on the calculation of features from call detail records (CDRs). Mobile network operators are often reluctant to provide access to CDRs due to commercial and privacy concerns. As a compromise, we show that a sparse CDR dataset combined with other publicly available datasets based on satellite imagery can yield competitive results. We construct a model using two CDR-based features, mobile ownership per capita and call volume per phone, combined with normalized satellite nightlight data and population density, to estimate the multi-dimensional poverty index (MPI) at the sector level in Rwanda. Our model accurately estimates the MPI for sectors in Rwanda containing mobile phone cell towers, achieving a cross-validated correlation of 0.88.