| 来源类型 | Working Paper |
| 规范类型 | 报告 |
| DOI | 10.3386/w29070 |
| 来源ID | Working Paper 29070 |
| Machine Learning and Mobile Phone Data Can Improve the Targeting of Humanitarian Assistance | |
| Emily Aiken; Suzanne Bellue; Dean Karlan; Christopher R. Udry; Joshua Blumenstock | |
| 发表日期 | 2021-07-26 |
| 出版年 | 2021 |
| 语种 | 英语 |
| 摘要 | The COVID-19 pandemic has devastated many low- and middle-income countries, causing widespread food insecurity and a sharp decline in living standards. In response to this crisis, governments and humanitarian organizations worldwide have distributed social assistance to over 1.5 billion people. Targeting is a central challenge in administering these programs: given available data, how does one rapidly identify those with the greatest need? Here we show that data from mobile phone networks can improve the targeting of humanitarian assistance. Our approach uses traditional survey data to train machine-learning algorithms to recognize patterns of poverty in mobile phone data; the trained algorithms can then prioritize aid to the poorest mobile subscribers. We evaluate this approach by studying Togo’s flagship emergency cash transfer program, which used these algorithms to disburse millions of dollars in COVID-19 relief aid. Our analysis compares outcomes – including exclusion errors, total social welfare, and measures of fairness – under different targeting regimes. Relative to the geographic targeting options considered by the Government of Togo, the machine learning approach reduces errors of exclusion by 4-21%. Relative to methods requiring a comprehensive social registry (a hypothetical exercise; no such registry exists in Togo), the machine learning approach increases exclusion errors by 9-35%. These results highlight the potential for new data sources to complement traditional methods for targeting humanitarian assistance, particularly in crisis settings when traditional data are missing or out of date. |
| 主题 | Econometrics ; Estimation Methods ; Health, Education, and Welfare ; Poverty and Wellbeing ; Development and Growth ; Development ; Innovation and R& ; D ; COVID-19 |
| URL | https://www.nber.org/papers/w29070 |
| 来源智库 | National Bureau of Economic Research (United States) |
| 引用统计 | |
| 资源类型 | 智库出版物 |
| 条目标识符 | http://119.78.100.153/handle/2XGU8XDN/586744 |
| 推荐引用方式 GB/T 7714 | Emily Aiken,Suzanne Bellue,Dean Karlan,et al. Machine Learning and Mobile Phone Data Can Improve the Targeting of Humanitarian Assistance. 2021. |
| 条目包含的文件 | ||||||
| 文件名称/大小 | 资源类型 | 版本类型 | 开放类型 | 使用许可 | ||
| w29070.pdf（2611KB） | 智库出版物 | 限制开放 | CC BY-NC-SA | 浏览 | ||
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。
