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.

In a recent study published in the journal Nature, researchers developed and evaluated an approach that used machine-learning algorithms to analyze mobile phone and satellite data to estimate poverty. They aimed to optimize the'Novissi' flagship emergency social assistance program in Togo, West Africa, providing subsistence cash relief to those most affected by COVID-19. Study: Machine learning and phone data can improve targeting of humanitarian aid. The coronavirus disease 2019 (COVID-19) pandemic has had devastating consequences in low- and lower-middle-income countries (LMICs). The living standards of the most economically vulnerable individuals have further worsened with a transition toward extreme poverty.

The COVID-19 pandemic has devastated many low- and middle-income countries, causing widespread food insecurity and a sharp decline in living standards1. In response to this crisis, governments and humanitarian organizations worldwide have distributed social assistance to more than 1.5 billion people2. Targeting is a central challenge in administering these programmes: it remains a difficult task to rapidly identify those with the greatest need given available data3,4. 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 a flagship emergency cash transfer program in Togo, which used these algorithms to disburse millions of US dollars worth of 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 in which traditional data are missing or out of date. Machine-learning algorithms can take advantage of survey and mobile phone data to help to identify people most in need of aid, complementing traditional methods for targeting humanitarian assistance.