Predicting socio-economic well-being using mobile apps data: a case study of France

Socio-economic indicators provide context for assessing a country’s overall condition. These indicators contain information about education, gender, poverty, employment, and other factors. Therefore, reliable and accurate information is critical for social research and government policing. Most data sources available today, such as censuses, have sparse population coverage or are updated infrequently. Nonetheless, alternative data sources, such as call data records (CDR) and mobile app usage, can serve as cost-effective and up-to-date sources for identifying socio-economic indicators. This work investigates mobile app data to predict socio-economic features. We present a large-scale study using data that captures the traffic of thousands of mobile applications by approximately 30 million users distributed over 550,000 km $$^2$$ 2 and served by over 25,000 base stations. The dataset covers the whole France territory and spans more than 2.5 months, starting from 16 th March 2019 to 6 th June 2019. We extracted three key patterns from mobile app data for each IRIS region: (1) Typical Week Signature (TWS) reflects patterns in how people use mobile apps during a typical week, while (2) Revealed Comparative Advantage (RCA) shows which app categories are disproportionately popular in specific regions compared to national averages, and Standardized Cumulative Utilization (SCU) measures the relative intensity of app usage across different time-periods. Using the app usage patterns, our best model can estimate socio-economic indicators (attaining an R-squared score up to 0.66). Furthermore, using models’ explainability, we discover that mobile app usage patterns have the potential to reveal socio-economic disparities in IRIS(IRIS is a region used to divide the country into units of similar population size.). Insights of this study provide several avenues for future interventions, including user temporal network analysis to understand evolving network patterns and exploration of alternative data sources.