Probing the limits of mobile phone metadata for poverty prediction and impact evaluation
Datos Bibliográficos
| ID | 11887981 |
|---|---|
| Autores | Oscar Barriga‐Cabanillas (0009-0008-0459-1043, World Bank, autor de correspondencia), Joshua E Blumenstock (0000-0002-1813-7414, University of California, Berkeley), Travis J Lybbert (0000-0002-4905-4881, University of California, Davis), Daniel S Putman (0000-0002-2446-0103, California University of Pennsylvania) |
| Año | 2025 |
| Volumen | 174 |
| Páginas | 103462-103462 |
| Fecha de publicación | 2025-02-04 |
| Peer Reviewed | Sí |
| Open Access | Sí |
| Tipo | ARTICLE |
| Revista | Journal of Development Economics (JOURNAL) |
| Identificadores de la revista | ISSN: 0304-3878 • E-ISSN: 1872-6089 |
| Editorial | Elsevier BV (PUBLISHER) |
| DOI | 10.1016/j.jdeveco.2025.103462 |
| OpenAlex | W4407133145 |
| Idioma | EN |
| Citas recibidas | 3 |
| Referencias citadas | 19 |
A series of recent papers demonstrate that mobile phone metadata can, together with machine learning, estimate the wealth of individual subscribers and accurately target cash transfer programs. In the context of an emergency cash transfer program in Haiti, we combine surveys and mobile phone call detail records (CDR) to test whether such methods can be used to estimate the program’s impact on household expenditures . We find that CDR-based predictions of total and food expenditures are much less accurate than predictions of wealth—particularly when estimated on a relatively homogeneous sample of rural communities eligible for the program. While impact estimates based on conventional survey data are positive and statistically significant, estimates based on CDR predictions are not statistically significant. In a postmortem discussion, we assess reasons for this failure and discuss the implications for using big data in poverty measurement and impact evaluation. • Mobile phone data and machine learning are better predictors of wealth than expenditure. • Prediction accuracy goes down when sampling from primarily poor households. • A tradeoff exists between data useful for program evaluation and for welfare prediction
Economic growth · Economics · Metadata · Mobile phone · Phone · Poverty · Telecommunications · World Wide Web · Computer Science · Human Mobility and Location-Based Analysis · ICT in Developing Communities
Calibration Estimators in Survey Sampling
Mapping poverty using mobile phone and satellite data
Quantifying the Impact of Human Mobility on Malaria
Combining satellite imagery and machine learning to predict poverty
Predicting poverty and wealth from mobile phone metadata
Manipulation of the running variable in the regression discontinuity design
Regression discontinuity designs
Regression Discontinuity Designs in Economics
Guidelines for Constructing Consumption Aggregates for Welfare Analysis
The economics of poverty traps and persistent poverty
Exploring Alternative Measures of Welfare in the Absence of Expenditure Data
Program targeting with machine learning and mobile phone data
Poor numbers. How we are misled by African development statistics and what to do about it
| Obras citantes distintas | 3 |
|---|---|
| Citas por año | 3 |
| Intervalo de citas | 2025 - 2025 (1) |
| Velocidad de citación | recent |
| Altamente citado | No |
| Tipos de cita | Neutras: 3 |