{"title":"三种多源推理模型对非洲财富指数预测的比较分析","authors":"Márton Karsai, János Kertész, Lisette Espín-Noboa","doi":"arxiv-2408.01631","DOIUrl":null,"url":null,"abstract":"Poverty map inference is a critical area of research, with growing interest\nin both traditional and modern techniques, ranging from regression models to\nconvolutional neural networks applied to tabular data, images, and networks.\nDespite extensive focus on the validation of training phases, the scrutiny of\nfinal predictions remains limited. Here, we compare the Relative Wealth Index\n(RWI) inferred by Chi et al. (2021) with the International Wealth Index (IWI)\ninferred by Lee and Braithwaite (2022) and Esp\\'in-Noboa et al. (2023) across\nsix Sub-Saharan African countries. Our analysis focuses on identifying trends\nand discrepancies in wealth predictions over time. Our results show that the\npredictions by Chi et al. and Esp\\'in-Noboa et al. align with general GDP\ntrends, with differences expected due to the distinct time-frames of the\ntraining sets. However, predictions by Lee and Braithwaite diverge\nsignificantly, indicating potential issues with the validity of the model.\nThese discrepancies highlight the need for policymakers and stakeholders in\nAfrica to rigorously audit models that predict wealth, especially those used\nfor decision-making on the ground. These and other techniques require\ncontinuous verification and refinement to enhance their reliability and ensure\nthat poverty alleviation strategies are well-founded.","PeriodicalId":501043,"journal":{"name":"arXiv - PHYS - Physics and Society","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Comparative Analysis of Wealth Index Predictions in Africa between three Multi-Source Inference Models\",\"authors\":\"Márton Karsai, János Kertész, Lisette Espín-Noboa\",\"doi\":\"arxiv-2408.01631\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Poverty map inference is a critical area of research, with growing interest\\nin both traditional and modern techniques, ranging from regression models to\\nconvolutional neural networks applied to tabular data, images, and networks.\\nDespite extensive focus on the validation of training phases, the scrutiny of\\nfinal predictions remains limited. Here, we compare the Relative Wealth Index\\n(RWI) inferred by Chi et al. (2021) with the International Wealth Index (IWI)\\ninferred by Lee and Braithwaite (2022) and Esp\\\\'in-Noboa et al. (2023) across\\nsix Sub-Saharan African countries. Our analysis focuses on identifying trends\\nand discrepancies in wealth predictions over time. Our results show that the\\npredictions by Chi et al. and Esp\\\\'in-Noboa et al. align with general GDP\\ntrends, with differences expected due to the distinct time-frames of the\\ntraining sets. However, predictions by Lee and Braithwaite diverge\\nsignificantly, indicating potential issues with the validity of the model.\\nThese discrepancies highlight the need for policymakers and stakeholders in\\nAfrica to rigorously audit models that predict wealth, especially those used\\nfor decision-making on the ground. These and other techniques require\\ncontinuous verification and refinement to enhance their reliability and ensure\\nthat poverty alleviation strategies are well-founded.\",\"PeriodicalId\":501043,\"journal\":{\"name\":\"arXiv - PHYS - Physics and Society\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Physics and Society\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2408.01631\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Physics and Society","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.01631","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
贫困图推断是一个重要的研究领域,人们对传统和现代技术的兴趣与日俱增,从回归模型到应用于表格数据、图像和网络的卷积神经网络,不一而足。在此,我们将 Chi 等人(2021 年)推断的相对财富指数(RWI)与 Lee 和 Braithwaite(2022 年)以及 Esp\'in-Noboa 等人(2023 年)在撒哈拉以南非洲六个国家推断的国际财富指数(IWI)进行比较。我们的分析重点是识别财富预测随时间变化的趋势和差异。我们的结果显示,Chi 等人和 Esp\'in-Noboa 等人的预测与 GDP 的总体趋势一致,由于训练集的时间框架不同,预计会存在差异。这些差异突出表明,非洲的政策制定者和利益相关者需要严格审核预测财富的模型,尤其是用于实地决策的模型。这些技术和其他技术需要不断验证和完善,以提高其可靠性,确保扶贫战略有充分的依据。
A Comparative Analysis of Wealth Index Predictions in Africa between three Multi-Source Inference Models
Poverty map inference is a critical area of research, with growing interest
in both traditional and modern techniques, ranging from regression models to
convolutional neural networks applied to tabular data, images, and networks.
Despite extensive focus on the validation of training phases, the scrutiny of
final predictions remains limited. Here, we compare the Relative Wealth Index
(RWI) inferred by Chi et al. (2021) with the International Wealth Index (IWI)
inferred by Lee and Braithwaite (2022) and Esp\'in-Noboa et al. (2023) across
six Sub-Saharan African countries. Our analysis focuses on identifying trends
and discrepancies in wealth predictions over time. Our results show that the
predictions by Chi et al. and Esp\'in-Noboa et al. align with general GDP
trends, with differences expected due to the distinct time-frames of the
training sets. However, predictions by Lee and Braithwaite diverge
significantly, indicating potential issues with the validity of the model.
These discrepancies highlight the need for policymakers and stakeholders in
Africa to rigorously audit models that predict wealth, especially those used
for decision-making on the ground. These and other techniques require
continuous verification and refinement to enhance their reliability and ensure
that poverty alleviation strategies are well-founded.