{"id":"W4403309424","doi":"10.1016/j.jdeveco.2024.103385","title":"Combining survey and census data for improved poverty prediction using semi-supervised deep learning","year":2024,"lang":"en","type":"article","venue":"Journal of Development Economics","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Becton Dickinson (Canada); Université de Sherbrooke","funders":"Mitacs; National Natural Science Foundation of China","keywords":"Census; Poverty; Survey data collection; Artificial intelligence; Machine learning; Deep learning; Econometrics; Computer science; Statistics; Geography; Demography; Economic growth; Economics; Mathematics; Sociology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00386519,0.00007401331,0.0001832688,0.0001193816,0.0004494612,0.0002467147,0.0001903051,0.00006498111,0.00002350045],"category_scores_gemma":[0.000404719,0.00007384356,0.00004120672,0.0001020994,0.00004507771,0.0004638219,0.00004845164,0.0001514558,7.844814e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002921716,"about_ca_system_score_gemma":0.0007701202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003013087,"about_ca_topic_score_gemma":0.002932252,"domain_scores_codex":[0.9990185,0.0001213344,0.0004704263,0.0001726384,0.00006814233,0.0001489091],"domain_scores_gemma":[0.9990971,0.0004083638,0.0001811308,0.00009083922,0.0001321497,0.00009042045],"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":[0.0003808455,0.000269765,0.2637761,0.0004158777,0.002348879,0.000007028905,0.05298211,0.02583521,0.0008666301,0.001644312,0.001535677,0.6499376],"study_design_scores_gemma":[0.0006076388,0.0000577302,0.01825623,0.0001003616,0.0001138979,0.000005411572,0.004724161,0.8820691,0.00004354537,0.0004331796,0.09337,0.0002188029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9702082,0.0005051336,0.02797866,0.000398294,0.000565498,0.0001457705,0.00006186037,0.00002085713,0.0001157153],"genre_scores_gemma":[0.9932387,0.0004357305,0.005767085,0.00007236436,0.0002137029,0.000001390331,0.0001564637,0.00001177115,0.0001027877],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8562338,"threshold_uncertainty_score":0.3456938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07285030285384858,"score_gpt":0.3123071568008434,"score_spread":0.2394568539469948,"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."}}