M. Merritt Smith, Emily Aiken, Joshua E. Blumenstock, Sveta Milusheva
arXiv 2 Feb 2026 · Econometrics · publishedAEA Papers and Proceedings (2026)
arXiv:2602.02805 · PDF · DOI · OpenAlex · Extracted main text
We provide systematic evidence on the potential for estimating household well-being from mobile phone data. Using data from four countries - Afghanistan, Cote d'Ivoire, Malawi, and Togo - we conduct parallel, standardized machine learning experiments to assess which measures of welfare can be most accurately predicted, which types of phone data are most useful, and how much training data is required. We find that long-term poverty measures such as wealth indices (Pearson's rho = 0.20-0.59) and multidimensional poverty (rho = 0.29-0.57) can be predicted more accurately than consumption (rho = 0.04 - 0.54); transient vulnerability measures like food security and mental health are very difficult to predict. Models using calls and text message behavior are more predictive than those using metadata on mobile internet usage, mobile money transactions, and airtime top-ups. Predictive accuracy improves rapidly through the first 1,000-2,000 training observations, with continued gains beyond 4,500 observations. Model performance depends strongly on sample heterogeneity: nationally-representative samples yield 20-70 percent higher accuracy than urban-only or rural-only samples.
appendix boundary found by none_found · 100% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Aiken, Emily and Bellue, Suzanne and Karlan, Dean and Udry, Chris an… (2022) Machine learning and phone data can improve targeting of humanitarian aid self | 0.644 | 2 | 2 | 100% |
| 2 | Aiken, Emily and Bedoya, Guadalupe and Blumenstock, Joshua and Covil… (2023) Program targeting with machine learning and mobile phone data: Evidence from an anti-poverty intervention in Afghanistan self | 0.644 | 2 | 2 | 100% |
| 3 | Aiken, Emily and Ohlenburg, Tim and Blumenstock, Joshua (2025) Moving targets: When does a poverty prediction model need to be updated? self | 0.405 | 1 | 1 | 100% |
| 4 | Aiken, Emily and Rolf, Esther and Blumenstock, Joshua (2023) Fairness and representation in satellite-based poverty maps: Evidence of urban-rural disparities and their impacts on downstream… self | 0.405 | 1 | 1 | 100% |
| 5 | Aiken, Emily and Ashraf, Anik and Blumenstock, Joshua and Guiteras,… (2025) Scalable Targeting of Social Protection: When Do Algorithms Out-Perform Surveys and Community Knowledge? self | 0.405 | 1 | 1 | 100% |
| 6 | Blumenstock, Joshua and Cadamuro, Gabriel and On, Robert (2015) Predicting poverty and wealth from mobile phone metadata self | 0.405 | 1 | 1 | 100% |
| 7 | Blumenstock, Joshua (2018) Estimating economic characteristics with phone data self | 0.405 | 1 | 1 | 100% |
| 8 | Blumenstock, Joshua Evan (2014) Calling for Better Measurement: Estimating an Individual’s Wealth and Well-Being from Mobile Phone Transaction Records self | 0.405 | 1 | 1 | 100% |
| 9 | Jerven, Morten (2013) Poor numbers: how we are misled by African development statistics and what to do about it | 0.405 | 1 | 1 | 100% |
| 10 | Steele, Jessica E. et al (2017) Mapping poverty using mobile phone and satellite data | 0.405 | 1 | 1 | 100% |
Showing the top 10 of 10 scored citations.