Cash in the City

Gentilini, Ugo; Khosla, Saksham; Almenfi, Mohamed

doi:10.1596/35003

Cited by 10 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we study one policy that has received substantial attention both within the COVID-19 crisis and more broadly as part of designing the social safety net in developing countries: a short-term unconditional cash transfer (UCT). By June 2020, 191 countries had initiated some form of cash transfers to combat the COVID-19 crisis ( Gentilini et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

Cash transfers as a response to COVID-19: Experimental evidence from Kenya

Brooks

Donovan

Johnson

et al. 2022

Journal of Development Economics

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Cash transfers as a response to COVID-19: Experimental evidence from Kenya

Brooks

Donovan

Johnson

et al. 2022

Journal of Development Economics

View full text Add to dashboard Cite

“…Gentilini et al, 2020), CDR-based targeting methods will likely play a more prominent role in the set of options considered by policymakers and program administrators -particularly in contexts like Afghanistan, where traditional targeting benchmarks are missing or of low quality. In just the past few years, for instance, data from mobile phone operators was used in the design of social assistance programs in Colombia, the Democratic Republic of the Congo, Pakistan, and Togo (Gentilini et al, 2020(Gentilini et al, , 2021Aiken et al, 2021). We conclude by highlighting a few policy important considerations for CDR-based targeting.…”

Section: Discussionmentioning

confidence: 98%

“…Encouragingly, the past several years have been characterized by a trend towards public sector access to CDR, particularly in the context of the COVID-19 pandemic, during which mobile network operators shared CDR with governments, researchers, and NGOs for social protection purposes (cf. Gentilini et al, 2020Gentilini et al, , 2021Aiken et al, 2021).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

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

Aiken¹,

Bedoya²,

Coville³

2022

Preprint

View full text Add to dashboard Cite

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.

show abstract

“…These ML-based estimates, which can be produced at a fraction of the cost of traditional survey-based methods of data collection, can fill in data gaps in poor, fragile, and conflict-affected regions where recent surveys do not exist [8]. And increasingly, the ML-based estimates are being used to inform critical policy decisions, including the targeting of humanitarian aid [9] and the allocation of social assistance [10,11].…”

Section: Introductionmentioning

confidence: 99%

Can Strategic Data Collection Improve the Performance of Poverty Prediction Models?

Soman¹,

Aiken²,

Rolf³

2022

Preprint

View full text Add to dashboard Cite

Machine learning-based estimates of poverty and wealth are increasingly being used to guide the targeting of humanitarian aid and the allocation of social assistance. However, the ground truth labels used to train these models are typically borrowed from existing surveys that were designed to produce national statistics -not to train machine learning models. Here, we test whether adaptive sampling strategies for ground truth data collection can improve the performance of poverty prediction models. Through simulations, we compare the status quo sampling strategies (uniform at random and stratified random sampling) to alternatives that prioritize acquiring training data based on model uncertainty or model performance on sub-populations. Perhaps surprisingly, we find that none of these active learning methods improve over uniform-at-random sampling. We discuss how these results can help shape future efforts to refine machine learning-based estimates of poverty.36th Conference on Neural Information Processing Systems (NeurIPS 2022).

show abstract

Cash in the City

Cited by 10 publications

References 0 publications

Cash transfers as a response to COVID-19: Experimental evidence from Kenya

Cash transfers as a response to COVID-19: Experimental evidence from Kenya

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

Can Strategic Data Collection Improve the Performance of Poverty Prediction Models?

Contact Info

Product

Resources

About