{"id":107,"date":"2017-03-13T14:16:06","date_gmt":"2017-03-13T18:16:06","guid":{"rendered":"https:\/\/www.bu.edu\/spark\/?p=107"},"modified":"2022-08-22T16:38:28","modified_gmt":"2022-08-22T20:38:28","slug":"deep-proxy-means-tests-using-deep-learning-to-assess-poverty-status","status":"publish","type":"post","link":"https:\/\/www.bu.edu\/spark\/2017\/03\/13\/deep-proxy-means-tests-using-deep-learning-to-assess-poverty-status\/","title":{"rendered":"Deep Proxy Means Tests: Using Deep Learning to Assess Poverty Status"},"content":{"rendered":"<p>This project includes using deep learning to improve asssesments\u00a0of \u00a0poverty for development organizations, such as the World Bank.<\/p>\n<p><strong><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;Jonathan Hersh, Assistant Professor, Chapman University&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:8403841,&quot;3&quot;:{&quot;1&quot;:0},&quot;10&quot;:2,&quot;11&quot;:4,&quot;12&quot;:0,&quot;14&quot;:{&quot;1&quot;:2,&quot;2&quot;:0},&quot;15&quot;:&quot;Arial&quot;,&quot;16&quot;:10,&quot;26&quot;:400}\">Project Lead:<\/span><\/strong><\/p>\n<p><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;Jonathan Hersh, Assistant Professor, Chapman University&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:8403841,&quot;3&quot;:{&quot;1&quot;:0},&quot;10&quot;:2,&quot;11&quot;:4,&quot;12&quot;:0,&quot;14&quot;:{&quot;1&quot;:2,&quot;2&quot;:0},&quot;15&quot;:&quot;Arial&quot;,&quot;16&quot;:10,&quot;26&quot;:400}\">Jonathan Hersh, Assistant Professor<\/span><br \/>\n<span>Economics and Management\u00a0Science,\u00a0<\/span><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;Jonathan Hersh, Assistant Professor, Chapman University&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:8403841,&quot;3&quot;:{&quot;1&quot;:0},&quot;10&quot;:2,&quot;11&quot;:4,&quot;12&quot;:0,&quot;14&quot;:{&quot;1&quot;:2,&quot;2&quot;:0},&quot;15&quot;:&quot;Arial&quot;,&quot;16&quot;:10,&quot;26&quot;:400}\">Chapman University<\/span><\/p>\n<p><strong>Detailed Project Description:<\/strong><\/p>\n<p><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;In development, a household's poverty status is most commonly determined through the use of a Proxy Means Tests (PMT). This is, at its heart, a probability model of poverty status on the basis of easily identifiable household characteristics such as the number of children, age of household members, their education, work status, and some easily identifiable assets. \\n \\n Most PMT models are estimated using either linear or binary models, and attain low levels of accuracy due to lack of sufficiently rich data and relatively simplistic models that are employed. Deep learning holds promise for PMT through the ability to discover and represent more complex relationships. This will allow for better and more efficient targeting of aid, and more accurate information on the distribution of the poor within a country. \\n \\n If successful, this will help inform poverty models built by development organizations such as the World Bank, as well as determine the effectiveness of deep learning models for applications in development.&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:8403841,&quot;3&quot;:{&quot;1&quot;:0},&quot;10&quot;:2,&quot;11&quot;:4,&quot;12&quot;:0,&quot;14&quot;:{&quot;1&quot;:2,&quot;2&quot;:0},&quot;15&quot;:&quot;Arial&quot;,&quot;16&quot;:10,&quot;26&quot;:400}\">In development, a household&#8217;s poverty status is most commonly determined through the use of a Proxy Means Tests (PMT). This is, at its heart, a probability model of poverty status on the basis of easily identifiable household characteristics such as the number of children, age of household members, their education, work status, and some easily identifiable assets.<\/span><\/p>\n<p>Most PMT models are estimated using either linear or binary models, and attain low levels of accuracy due to lack of sufficiently rich data and relatively simplistic models that are employed. Deep learning holds promise for PMT through the ability to discover and represent more complex relationships. This will allow for better and more efficient targeting of aid, and more accurate information on the distribution of the poor within a country.<\/p>\n<p>If successful, this will help inform poverty models built by development organizations such as the World Bank, as well as determine the effectiveness of deep learning models for applications in development.<\/p>\n<p><strong>Technical Components:<\/strong><\/p>\n<p><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;I need assistance completing this section;Software engineering;Mobile application development;Computer network security&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:8403841,&quot;3&quot;:{&quot;1&quot;:0},&quot;10&quot;:2,&quot;11&quot;:4,&quot;12&quot;:0,&quot;14&quot;:{&quot;1&quot;:2,&quot;2&quot;:0},&quot;15&quot;:&quot;Arial&quot;,&quot;16&quot;:10,&quot;26&quot;:400}\">I need assistance <span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;I need someone capable of building deep learning models in Python, and can train them using a limited set of observations (20k at most).&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:8403841,&quot;3&quot;:{&quot;1&quot;:0},&quot;10&quot;:2,&quot;11&quot;:4,&quot;12&quot;:0,&quot;14&quot;:{&quot;1&quot;:2,&quot;2&quot;:0},&quot;15&quot;:&quot;Arial&quot;,&quot;16&quot;:10,&quot;26&quot;:400}\">building deep learning models in Python, and can train them using a limited set of observations (20k at most).\u00a0<\/span><\/span><\/p>\n<p><strong>Skill\/Expertise Requirement(s):<\/strong><\/p>\n<p><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;I need someone capable of building deep learning models in Python, and can train them using a limited set of observations (20k at most).&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:8403841,&quot;3&quot;:{&quot;1&quot;:0},&quot;10&quot;:2,&quot;11&quot;:4,&quot;12&quot;:0,&quot;14&quot;:{&quot;1&quot;:2,&quot;2&quot;:0},&quot;15&quot;:&quot;Arial&quot;,&quot;16&quot;:10,&quot;26&quot;:400}\">1) Capable of building deep learning models in Python and can train them\u00a0<\/span><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;I need someone capable of building deep learning models in Python, and can train them using a limited set of observations (20k at most).&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:8403841,&quot;3&quot;:{&quot;1&quot;:0},&quot;10&quot;:2,&quot;11&quot;:4,&quot;12&quot;:0,&quot;14&quot;:{&quot;1&quot;:2,&quot;2&quot;:0},&quot;15&quot;:&quot;Arial&quot;,&quot;16&quot;:10,&quot;26&quot;:400}\">using a limited set of observations (20k at most).<\/span><\/p>\n<p><strong>Data Set(s):<\/strong><\/p>\n<p><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;I have access to a number of household surveys that identify household poverty status&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:8403841,&quot;3&quot;:{&quot;1&quot;:0},&quot;10&quot;:2,&quot;11&quot;:4,&quot;12&quot;:0,&quot;14&amp;quot{&quot;1&quot;:2,&quot;2&quot;:0},&quot;15&quot;:&quot;Arial&quot;,&quot;16&quot;:10,&quot;26&quot;:400}\">Household surveys that identify household poverty status.<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>This project includes using deep learning to improve asssesments\u00a0of \u00a0poverty for development organizations, such as the World Bank. Project Lead: Jonathan Hersh, Assistant Professor Economics and Management\u00a0Science,\u00a0Chapman University Detailed Project Description: In development, a household&#8217;s poverty status is most commonly determined through the use of a Proxy Means Tests (PMT). This is, at its heart, [&hellip;]<\/p>\n","protected":false},"author":8550,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[8,65],"tags":[13,16,15,14],"_links":{"self":[{"href":"https:\/\/www.bu.edu\/spark\/wp-json\/wp\/v2\/posts\/107"}],"collection":[{"href":"https:\/\/www.bu.edu\/spark\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.bu.edu\/spark\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/spark\/wp-json\/wp\/v2\/users\/8550"}],"replies":[{"embeddable":true,"href":"https:\/\/www.bu.edu\/spark\/wp-json\/wp\/v2\/comments?post=107"}],"version-history":[{"count":3,"href":"https:\/\/www.bu.edu\/spark\/wp-json\/wp\/v2\/posts\/107\/revisions"}],"predecessor-version":[{"id":131,"href":"https:\/\/www.bu.edu\/spark\/wp-json\/wp\/v2\/posts\/107\/revisions\/131"}],"wp:attachment":[{"href":"https:\/\/www.bu.edu\/spark\/wp-json\/wp\/v2\/media?parent=107"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.bu.edu\/spark\/wp-json\/wp\/v2\/categories?post=107"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.bu.edu\/spark\/wp-json\/wp\/v2\/tags?post=107"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}