{"id":"W4366490164","doi":"10.1111/poms.14018","title":"A machine learning approach to deal with ambiguity in the humanitarian decision‐making","year":2023,"lang":"en","type":"article","venue":"Production and Operations Management","topic":"Facility Location and Emergency Management","field":"Business, Management and Accounting","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Group for Research in Decision Analysis; Université du Québec à Montréal","funders":"","keywords":"Ambiguity; Computer science; Operations research; Cluster analysis; Humanitarian aid; Linear programming; Management science; Machine learning; Economics; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001089871,0.0001440109,0.0001043315,0.0005929127,0.0007013493,0.0003295587,0.0002014602,0.00001830973,0.00005280909],"category_scores_gemma":[0.00005247478,0.0001051831,0.00002165058,0.00174446,0.00002878555,0.0005139107,0.0001958948,0.0001284088,0.0002731571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003076995,"about_ca_system_score_gemma":0.000004702842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000529334,"about_ca_topic_score_gemma":0.00512419,"domain_scores_codex":[0.9987466,0.00002904753,0.0002410013,0.0004375254,0.0003219897,0.0002238008],"domain_scores_gemma":[0.9996288,0.000007219162,0.00002205502,0.0002588836,0.00007254237,0.00001047249],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007863456,0.0003457245,0.006665858,0.0002811207,0.00005521272,0.000008064924,0.001918946,0.6786509,0.000005857228,0.2187649,0.01040494,0.08281984],"study_design_scores_gemma":[0.000701174,0.00004694152,0.2009794,0.0001318861,0.0001030064,0.000004891339,0.01157164,0.2621575,0.000001480207,0.001920897,0.5218074,0.0005738058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6561869,0.000203903,0.08560374,0.04382187,0.0009993948,0.007350809,0.000004169219,0.00120946,0.2046197],"genre_scores_gemma":[0.9920878,0.00006304091,0.003601109,0.001761414,0.0002062158,0.0003661216,0.00005512472,0.00001432795,0.001844893],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5114025,"threshold_uncertainty_score":0.5394283,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03450633846651197,"score_gpt":0.2567275911369589,"score_spread":0.222221252670447,"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."}}