{"id":{"repo_id":"cornell","oai_identifier":"oai:ecommons.cornell.edu:1813/112156"},"canonical_url":"https://search.dev.ndltd.org/etd/cornell/oai:ecommons.cornell.edu:1813/112156","repository":{"repo_id":"cornell","name":"Cornell University","base_url":"https://ecommons.cornell.edu/server/oai/request"},"display":{"title":"Asset-Based Measures for Machine-Learning Poverty Maps","abstract":"This paper develops a machine learning approach to estimate internationally-and-intertemporally comparable, decomposable, structural asset poverty measures. These measures are founded in theory, link directly to official poverty lines, and are amenable to ML-based prediction using Earth Observation data. Using household survey data from Tanzania, Uganda, and Malawi, we model the relationship between household consumption expenditures and productive assets, directly linking flow-based poverty measures with asset-based structural poverty measures. The poverty measures we construct can serve as new, improved dependent variables for ML poverty prediction. We also assess whether our poverty estimates vary from readily available poverty estimates and whether this difference in poverty measures matters.","abstract_html":"This paper develops a machine learning approach to estimate internationally-and-intertemporally comparable, decomposable, structural asset poverty measures. These measures are founded in theory, link directly to official poverty lines, and are amenable to ML-based prediction using Earth Observation data. Using household survey data from Tanzania, Uganda, and Malawi, we model the relationship between household consumption expenditures and productive assets, directly linking flow-based poverty measures with asset-based structural poverty measures. The poverty measures we construct can serve as new, improved dependent variables for ML poverty prediction. We also assess whether our poverty estimates vary from readily available poverty estimates and whether this difference in poverty measures matters.","abstract_has_math":false,"creators":["Sheng, Peizan"],"institution":"Cornell University","degree_name":"M.S., Applied Economics and Management","degree_level":"Master of Science","degree_discipline":"Applied Economics and Management","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":["Barrett, Chris"],"year":2022,"date_issued":"2022-08","date_published":"2022-08","updated_at":"2026-07-24T01:48:58Z","subjects":[],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.7298/5h31-bk67"],"render_values":[{"text":"https://doi.org/10.7298/5h31-bk67","href":"https://doi.org/10.7298/5h31-bk67","code":true}]},{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["ProQuest Submission ID: 11518","ProQuest Publication ID: 29261446"],"render_values":[{"text":"ProQuest Submission ID: 11518","href":null,"code":true},{"text":"ProQuest Publication ID: 29261446","href":null,"code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/1813/112156","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Barrett, Chris"]},{"key":"dc:creator","label":"Author","values":["Sheng, Peizan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2022-10-31T16:24:02Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2022-10-31T16:24:02Z"]},{"key":"dc:date.issued","label":"Date","values":["2022-08"]},{"key":"dc:type","label":"Dc Type","values":["dissertation or thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Applied Economics and Management"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Master of Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S., Applied Economics and Management"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Cornell University"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.7298/5h31-bk67"]},{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["ProQuest Submission ID: 11518","ProQuest Publication ID: 29261446"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1813/112156"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["101 pages"]},{"key":"dc:description.abstract","label":"Abstract","values":["This paper develops a machine learning approach to estimate internationally-and-intertemporally comparable, decomposable, structural asset poverty measures. These measures are founded in theory, link directly to official poverty lines, and are amenable to ML-based prediction using Earth Observation data. Using household survey data from Tanzania, Uganda, and Malawi, we model the relationship between household consumption expenditures and productive assets, directly linking flow-based poverty measures with asset-based structural poverty measures. The poverty measures we construct can serve as new, improved dependent variables for ML poverty prediction. We also assess whether our poverty estimates vary from readily available poverty estimates and whether this difference in poverty measures matters."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Asset-Based Measures for Machine-Learning Poverty Maps"]}]}],"canonical_facts":{"dc:contributor.committeemember":["Barrett, Chris"],"dc:creator":["Sheng, Peizan"],"dc:date.accessioned":["2022-10-31T16:24:02Z"],"dc:date.available":["2022-10-31T16:24:02Z"],"dc:date.issued":["2022-08"],"dc:description":["101 pages"],"dc:description.abstract":["This paper develops a machine learning approach to estimate internationally-and-intertemporally comparable, decomposable, structural asset poverty measures. These measures are founded in theory, link directly to official poverty lines, and are amenable to ML-based prediction using Earth Observation data. Using household survey data from Tanzania, Uganda, and Malawi, we model the relationship between household consumption expenditures and productive assets, directly linking flow-based poverty measures with asset-based structural poverty measures. The poverty measures we construct can serve as new, improved dependent variables for ML poverty prediction. We also assess whether our poverty estimates vary from readily available poverty estimates and whether this difference in poverty measures matters."],"dc:format.mimetype":["application/pdf"],"dc:identifier.doi":["https://doi.org/10.7298/5h31-bk67"],"dc:identifier.other":["ProQuest Submission ID: 11518","ProQuest Publication ID: 29261446"],"dc:identifier.uri":["https://hdl.handle.net/1813/112156"],"dc:language.iso":["en"],"dc:title":["Asset-Based Measures for Machine-Learning Poverty Maps"],"dc:type":["dissertation or thesis"],"thesis:degree_discipline":["Applied Economics and Management"],"thesis:degree_level":["Master of Science"],"thesis:degree_name":["M.S., Applied Economics and Management"],"thesis:institution_name":["Cornell University"]},"updated_at":"2026-07-24T01:48:58Z"}