EconBase
← All papers

Enhancing Poverty Targeting with Spatial Machine Learning: An application to Indonesia

Rolando Gonzales Martinez, Mariza Cooray

arXiv 6 Mar 2025 · Econometrics

arXiv:2503.04300 · PDF · DOI · OpenAlex · Extracted main text

Abstract

This study leverages spatial machine learning (SML) to enhance the accuracy of Proxy Means Testing (PMT) for poverty targeting in Indonesia. Conventional PMT methodologies are prone to exclusion and inclusion errors due to their inability to account for spatial dependencies and regional heterogeneity. By integrating spatial contiguity matrices, SML models mitigate these limitations, facilitating a more precise identification and comparison of geographical poverty clusters. Utilizing household survey data from the Social Welfare Integrated Data Survey (DTKS) for the periods 2016 to 2020 and 2016 to 2021, this study examines spatial patterns in income distribution and delineates poverty clusters at both provincial and district levels. Empirical findings indicate that the proposed SML approach reduces exclusion errors from 28% to 20% compared to standard machine learning models, underscoring the critical role of spatial analysis in refining machine learning-based poverty targeting. These results highlight the potential of SML to inform the design of more equitable and effective social protection policies, particularly in geographically diverse contexts. Future research can explore the applicability of spatiotemporal models and assess the generalizability of SML approaches across varying socio-economic settings.

Citation extraction

25
references
28
in-text mentions
25
distinct cited
0
self-citations
7,064
main-text words

appendix boundary found by appendix_titled_section at “Appendix 1: results at province level (data 2016-2020)” · 88% of the source is main text. Read the extracted text to check this.

Most heavily cited references

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.

ReferenceIntensityMentionsSectionsMain text
1L. McBride and A. Nichols (2018) Retooling poverty targeting using out-of-sample validation and machine learning0.51121100%
2P. Schnitzer and Q. Stoeffler (2023) Targeting social safety nets: Evidence from nine programs in the sahel0.51121100%
3M. Solís-Salazar and J. Madrigal-Sanabria (2022) A machine learning proposal to predict poverty0.51121100%
4E. Aiken, S. Bellue, D. Karlan, C. Udry, and J. E. Blumenstock (2022) Machine learning and phone data can improve targeting of humanitarian aid0.40511100%
5V. Alatas, A. Banerjee, R. Hanna, B. A. Olken, and J. Tobias (2012) Targeting the poor: evidence from a field experiment in indonesia0.40511100%
6S. Alkire and J. Foster (2011) Counting and multidimensional poverty measurement0.40511100%
7C. Brown, M. Ravallion, and D. Van de Walle (2018) A poor means test? econometric targeting in africa0.40511100%
8D. Coady, M. E. Grosh, and J. Hoddinott (2004) Targeting of transfers in developing countries: Review of lessons and experience0.40511100%
9P. Corral, H. Henderson, and S. Segovia (2025) Poverty mapping in the age of machine learning0.40511100%
10S. Dietrich, D. Malerba, and F. Gassmann (2023) Predicting social assistance beneficiaries: On the social welfare damage of data biases0.40511100%

Showing the top 10 of 25 scored citations.