Program Targeting with Machine Learning and Mobile Phone Data: Evidence from an Anti-Poverty Intervention in Afghanistan

• URL: http://arxiv.org/abs/2206.11400v1
• Date: Wed, 22 Jun 2022 22:03:24 GMT
• Title: Program Targeting with Machine Learning and Mobile Phone Data: Evidence from an Anti-Poverty Intervention in Afghanistan
• Authors: Emily Aiken, Guadalupe Bedoya, Joshua Blumenstock, Aidan Coville
• Abstract summary: We show that machine learning methods can identify ultra-poor households nearly as accurately as survey-based measures of consumption and wealth. We show that combining survey-based measures with mobile phone data produces classifications more accurate than those based on a single data source.
• Score: 0.6554326244334867
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Can mobile phone data improve program targeting? By combining rich survey data from a "big push" anti-poverty program in Afghanistan with detailed mobile phone logs from program beneficiaries, we study the extent to which machine learning methods can accurately differentiate ultra-poor households eligible for program benefits from ineligible households. We show 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.

Related papers

• Incremental Semi-supervised Federated Learning for Health Inference via Mobile Sensing [5.434366992553875]
  We propose FedMobile, an incremental semi-supervised federated learning algorithm. We evaluate FedMobile using a real-world mobile sensing dataset for influenza-like symptom recognition.
  arXiv  Detail & Related papers  (2023-12-19T23:39:33Z)
• Viability of Mobile Forms for Population Health Surveys in Low Resource Areas [47.28991543521559]
  Population health surveys are an important tool to effectively allocate limited resources in low resource communities. Data thus collected is difficult to tabulate and analyze. We conducted a series of interviews and experiments in the Philippines to assess if mobile forms can be a viable and more efficient survey method.
  arXiv  Detail & Related papers  (2023-10-11T20:51:28Z)
• An Ensemble Mobile-Cloud Computing Method for Affordable and Accurate Glucometer Readout [0.0]
  We present an ensemble learning algorithm, a mobile-cloud computing service architecture, and a simple compression technique to achieve higher availability and faster response time. Our proposed method achieves 92.1% and 97.7% accuracy on two different datasets, improving previous methods by 40%, (2) reducing required bandwidth by 45x with 1% drop in accuracy, (3) and providing better availability compared to mobile-only, cloud-only, split computing, and early exit service models.
  arXiv  Detail & Related papers  (2023-01-04T18:48:53Z)
• Error-Aware Imitation Learning from Teleoperation Data for Mobile Manipulation [54.31414116478024]
  In mobile manipulation (MM), robots can both navigate within and interact with their environment. In this work, we explore how to apply imitation learning (IL) to learn continuous visuo-motor policies for MM tasks.
  arXiv  Detail & Related papers  (2021-12-09T23:54:59Z)
• Understanding the World Through Action [91.3755431537592]
  I will argue that a general, principled, and powerful framework for utilizing unlabeled data can be derived from reinforcement learning. I will discuss how such a procedure is more closely aligned with potential downstream tasks.
  arXiv  Detail & Related papers  (2021-10-24T22:33:52Z)
• Leveraging Mobile Phone Data for Migration Flows [5.0161988361764775]
  Statistics on migration flows are often derived from census data, which suffer from intrinsic limitations. Alternative data sources, such as surveys and field observations, also suffer from reliability, costs, and scale limitations. The ubiquity of mobile phones enables an accurate and efficient collection of up-to-date data related to migration.
  arXiv  Detail & Related papers  (2021-05-31T13:41:47Z)
• Deploying machine learning to assist digital humanitarians: making image annotation in OpenStreetMap more efficient [72.44260113860061]
  We propose an interactive method to support and optimize the work of volunteers in OpenStreetMap. The proposed method greatly reduces the amount of data that the volunteers of OSM need to verify/correct.
  arXiv  Detail & Related papers  (2020-09-17T10:05:30Z)
• Urban Sensing based on Mobile Phone Data: Approaches, Applications and Challenges [67.71975391801257]
  Much concern in mobile data analysis is related to human beings and their behaviours. This work aims to review the methods and techniques that have been implemented to discover knowledge from mobile phone data.
  arXiv  Detail & Related papers  (2020-08-29T15:14:03Z)
• Predicting cell phone adoption metrics using satellite imagery [1.2691047660244335]
  Approximately half of the global population does not have access to the internet, even though digital connectivity can reduce poverty by revolutionizing economic development opportunities. Mobile Network Operators and governments struggle to effectively determine if infrastructure investments are viable, especially in greenfield areas where demand is unknown. We present a machine learning method that uses publicly available satellite imagery to predict telecoms demand metrics, including cell phone adoption and spending on mobile services, and apply the method to Malawi and Ethiopia.
  arXiv  Detail & Related papers  (2020-06-12T16:47:45Z)
• Generating Interpretable Poverty Maps using Object Detection in Satellite Images [80.35540308137043]
  We demonstrate an interpretable computational framework to accurately predict poverty at a local level by applying object detectors to satellite images. Using the weighted counts of objects as features, we achieve 0.539 Pearson's r2 in predicting village-level poverty in Uganda, a 31% improvement over existing (and less interpretable) benchmarks.
  arXiv  Detail & Related papers  (2020-02-05T02:50:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.