{"id":"W4388624949","doi":"10.2139/ssrn.4631449","title":"Combining Survey and Census Data for Improved Poverty Prediction Using Semi-Supervised Deep Learning","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Census; Poverty; Survey data collection; Deep learning; American Community Survey; Artificial intelligence; Machine learning; Statistics; Geography; Computer science; Econometrics; Mathematics; Demography; Economic growth; Economics; Sociology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00104897,0.0007996442,0.001034318,0.001708607,0.0003546376,0.0006258135,0.001315912,0.0009297148,0.002555752],"category_scores_gemma":[0.003792698,0.0004353423,0.0009156656,0.002331325,0.0002976873,0.001226085,0.001477515,0.001133315,0.001375669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00060001,"about_ca_system_score_gemma":0.00104243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01805385,"about_ca_topic_score_gemma":0.02763698,"domain_scores_codex":[0.9995006,0.0001761139,0.00003064686,0.0001316691,0.00006158131,0.00009937738],"domain_scores_gemma":[0.9986188,0.0006499688,0.0001349744,0.0001906002,0.0003197793,0.00008588327],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004963945,0.001225507,0.1050219,0.0002364317,0.0005433689,0.0002080482,0.0002115001,0.3749571,0.002169838,0.002983706,0.02203498,0.4899113],"study_design_scores_gemma":[0.000006961364,0.00002019949,0.003899847,0.00001308167,0.00001577021,0.00001209234,0.00003242156,0.9929926,0.0003009995,0.002274038,0.0004254451,0.000006577198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4385058,0.001020946,0.5438178,0.001385716,0.0002452828,0.000119047,0.008392348,0.00344777,0.003065452],"genre_scores_gemma":[0.948966,0.0002007926,0.04110618,0.0001810198,0.00009969225,0.0001230593,0.006658597,0.00005495561,0.002609689],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01805385,"threshold_uncertainty_score":0.03589755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08075252628813522,"score_gpt":0.3423030498362135,"score_spread":0.2615505235480782,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}