|
|
|
|
| LEADER |
02042nmm a2200385 u 4500 |
| 001 |
EB002177632 |
| 003 |
EBX01000000000000001315166 |
| 005 |
00000000000000.0 |
| 007 |
cr||||||||||||||||||||| |
| 008 |
231006 ||| eng |
| 100 |
1 |
|
|a Emily L., Aiken
|
| 245 |
0 |
0 |
|a Program Targeting with Machine Learning and Mobile Phone Data
|h Elektronische Ressource
|b Evidence from an Anti-Poverty Intervention in Afghanistan
|c Aiken Emily L
|
| 260 |
|
|
|a Washington, D.C
|b The World Bank
|c 2022
|
| 300 |
|
|
|a 47 pages
|
| 653 |
|
|
|a Information Technology
|
| 653 |
|
|
|a Targeting
|
| 653 |
|
|
|a Targeting Ultra-Poor Household Data
|
| 653 |
|
|
|a Recipients
|
| 653 |
|
|
|a Machine Learning
|
| 653 |
|
|
|a Science and Technology Development
|
| 653 |
|
|
|a Information and Communication Technologies
|
| 653 |
|
|
|a Poverty Reduction
|
| 653 |
|
|
|a Services and Transfers to Poor
|
| 653 |
|
|
|a Innovation
|
| 653 |
|
|
|a Cash Transfers
|
| 653 |
|
|
|a Mobile Phone Data
|
| 700 |
1 |
|
|a Coville, Aidan
|
| 700 |
1 |
|
|a Joshua E., Blumenstock
|
| 700 |
1 |
|
|a Bedoya, Guadalupe
|
| 041 |
0 |
7 |
|a eng
|2 ISO 639-2
|
| 989 |
|
|
|b WOBA
|a World Bank E-Library Archive
|
| 028 |
5 |
0 |
|a 10.1596/1813-9450-10252
|
| 856 |
4 |
0 |
|u http://elibrary.worldbank.org/doi/book/10.1596/1813-9450-10252
|x Verlag
|3 Volltext
|
| 082 |
0 |
|
|a 330
|
| 520 |
|
|
|a Can mobile phone data improve program targeting By combining rich survey data from the baseline of a "big push" anti-poverty program in Afghanistan implemented in 2016 with detailed mobile phone logs from program beneficiaries, this paper studies the extent to which machine learning methods can accurately differentiate ultra-poor households eligible for program benefits from ineligible households. The paper shows that machine learning methods leveraging mobile phone data can identify ultra-poor households nearly as accurately as survey-based measures of consumption and wealth; and that combining survey-based measures with mobile phone data produces classifications more accurate than those based on a single data source
|