{"corpus_id":234097333,"paper_sha":"7ceaa167d3a41af5477961bb042a246aaceb4b17","doi":"10.3390/SU13031412","arxiv_id":null,"pmid":null,"pmcid":null,"mag_id":3128861468,"dblp_id":null,"acl_id":null,"title":"Poverty Classification Using Machine Learning: The Case of Jordan","year":2021,"publication_date":"2021-01-29","venue":"","journal":{"name":"Sustainability","pages":"1412","volume":"13"},"journal_issn":null,"journal_title":null,"publication_types":["Review"],"pubmed_pub_types":null,"s2_fields_of_study":["Computer Science","Economics"],"reference_count":31,"citation_count":61,"influential_citation_count":4,"is_open_access":true,"arxiv_categories":null,"arxiv_license":null,"arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":1,"s2_open_access_pdf_url":"https://www.mdpi.com/2071-1050/13/3/1412/pdf?version=1611917364","s2_open_access_landing_url":"https://www.semanticscholar.org/paper/7ceaa167d3a41af5477961bb042a246aaceb4b17","s2_open_access_license":"CCBY","s2_open_access_status":"GOLD","pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"The scope of this paper is focused on the multidimensional poverty problem in Jordan. Household expenditure and income surveys provide data that are used for identifying and measuring the poverty status of Jordanian households. However, carrying out such surveys is hard, time consuming, and expensive. Machine learning could revolutionize this process. The contribution of this work is the proposal of an original machine learning approach to assess and monitor the poverty status of Jordanian households. This approach takes into account all the household expenditure and income surveys that took place since the early beginning of the new millennium. This approach is accurate, inexpensive, and makes poverty identification cheaper and much closer to real-time. Data preprocessing and handling imbalanced data are major parts of this work. Various machine learning classification models are applied. The LightGBM algorithm has achieved the best performance with 81% F1-Score. The final machine learning classification model could transform efforts to track and target poverty across the country. This work demonstrates how powerful and versatile machine learning can be, and hence, it promotes for adoption across many domains in both the private sector and government.","claims":[{"public_id":"cl_230e001ae36b1d9eeb268f2fc101c5a9","status":"active","text":"An original machine learning approach is proposed to assess and monitor the poverty status of Jordanian households using household expenditure and income surveys since the early beginning of the new millennium.","confidence":0.97,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_230e001ae36b1d9eeb268f2fc101c5a9"},{"public_id":"cl_7fd7354362c015cfb7a0b57be0ceeeb9","status":"active","text":"Data preprocessing and handling imbalanced data are major components of the classification workflow.","confidence":0.91,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_7fd7354362c015cfb7a0b57be0ceeeb9"},{"public_id":"cl_a8ce7a9014b6b3f95165d55850959f12","status":"active","text":"LightGBM achieved the best performance with an 81% F1-Score among the evaluated classification models.","confidence":0.98,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_a8ce7a9014b6b3f95165d55850959f12"},{"public_id":"cl_92df3a3dff056787fd31436bb651df25","status":"active","text":"The final machine learning classification model can make poverty identification cheaper and closer to real-time.","confidence":0.93,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_92df3a3dff056787fd31436bb651df25"}],"concepts":[{"public_id":"co_25d744e5264cc478fff7efa3f3bf34e2","status":"active","name":"machine learning classification model","description":"A trained model that predicts poverty-related class labels from survey features.","types":["model"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_25d744e5264cc478fff7efa3f3bf34e2"},{"public_id":"co_33439d14b3bb38f06f4e1c67747f523a","status":"active","name":"poverty status","description":"The measured or predicted poverty condition of a household.","types":["outcome","measure"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_33439d14b3bb38f06f4e1c67747f523a"},{"public_id":"co_65d98d73c59ea13799c7d17ca3158afb","status":"active","name":"machine learning approach","description":"A computational approach that uses machine learning models to classify or estimate poverty status from survey data.","types":["method"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_65d98d73c59ea13799c7d17ca3158afb"},{"public_id":"co_7be2cd506b7175ecc907b88ad2463147","status":"active","name":"LightGBM","description":"A gradient boosting decision tree algorithm used here as one of the evaluated classifiers.","types":["algorithm","model"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_7be2cd506b7175ecc907b88ad2463147"},{"public_id":"co_99ce9678e3e4e42faff878583ea86705","status":"active","name":"poverty identification","description":"The process of determining whether a household is poor or non-poor.","types":["task"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_99ce9678e3e4e42faff878583ea86705"},{"public_id":"co_ac91ce8385d92c6ffe47fb636be0719d","status":"active","name":"classification models","description":"Machine learning models used to assign households to poverty-related classes.","types":["method"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_ac91ce8385d92c6ffe47fb636be0719d"},{"public_id":"co_bf697e610c721d75cfb7fa0543f55805","status":"active","name":"Jordanian households","description":"Households in Jordan that are the units of analysis for poverty classification.","types":["population"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_bf697e610c721d75cfb7fa0543f55805"},{"public_id":"co_c55c7de57bfc48830a2b805fee011513","status":"active","name":"F1-Score","description":"An evaluation metric that balances precision and recall for classification performance.","types":["evaluation metric"],"aliases":["F1 score"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_c55c7de57bfc48830a2b805fee011513"},{"public_id":"co_c8e604627dccdb5965e3c98c3f49a227","status":"active","name":"imbalanced data","description":"Training data in which poverty classes are unevenly represented.","types":["data characteristic"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_c8e604627dccdb5965e3c98c3f49a227"},{"public_id":"co_ce12e7506a240680de695738aa8b819b","status":"active","name":"real-time monitoring","description":"Near-immediate updating or assessment of poverty status over time.","types":["monitoring approach"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_ce12e7506a240680de695738aa8b819b"},{"public_id":"co_d0493146db2358bfe16ff8e68048eee7","status":"active","name":"household expenditure and income surveys","description":"Survey datasets containing household spending and income information used to identify poverty status.","types":["dataset","survey"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_d0493146db2358bfe16ff8e68048eee7"},{"public_id":"co_d5fa2e5301af3ef2f6c1ce746d82838f","status":"active","name":"data preprocessing","description":"Steps used to clean, transform, and prepare the survey data for model training.","types":["method"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_d5fa2e5301af3ef2f6c1ce746d82838f"}],"external_ids":{"DOI":"10.3390/SU13031412","ArXiv":null,"PubMed":null,"PubMedCentral":null,"MAG":3128861468,"DBLP":null,"ACL":null},"open_access":{"is_open_access":true,"pdf_url":"https://www.mdpi.com/2071-1050/13/3/1412/pdf?version=1611917364","landing_url":"https://www.semanticscholar.org/paper/7ceaa167d3a41af5477961bb042a246aaceb4b17","source":"semantic_scholar","pdf_url_source":"semantic_scholar_open_access_pdf","license":"CCBY","status":"GOLD","reason":null},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":false,"full_text_source":null,"count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":1},"paper_id":632738,"paper_uid":"441c4505-735b-4aa2-b433-ddfdbfa81fbb","canonical_identity":{"paper_id":632738,"paper_uid":"441c4505-735b-4aa2-b433-ddfdbfa81fbb","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/234097333"}