{"id":"W7116880710","doi":"10.1016/j.dajour.2025.100668","title":"An analysis of machine learning approaches for enhancing decision-making in complex discrete choice tasks","year":2025,"lang":"en","type":"article","venue":"Decision Analytics Journal","topic":"Economic and Environmental Valuation","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Division of Social and Economic Sciences; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Discrete choice; Preference learning; Preference; Context (archaeology); Preference elicitation; Parametric statistics; Representation (politics); Inference","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":[0.002313718,0.0001501344,0.000681209,0.001731646,0.0001855407,0.0001236081,0.0003168053,0.00009719474,0.000473565],"category_scores_gemma":[0.0007612227,0.0001606313,0.0003357241,0.0007945098,0.0000398805,0.0002835908,0.00006563513,0.0002599159,0.00001171237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000296853,"about_ca_system_score_gemma":0.0000202364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004942436,"about_ca_topic_score_gemma":0.0007818127,"domain_scores_codex":[0.9978762,0.0000352385,0.001422842,0.000357171,0.00007768526,0.0002309002],"domain_scores_gemma":[0.9981276,0.0007696995,0.0007260985,0.0002733645,0.00002969355,0.00007355892],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004493262,0.0000677174,0.5326815,0.000005669979,0.0002345216,7.24145e-7,0.000142339,0.4439379,0.00001679835,0.004610086,0.00003120055,0.0182266],"study_design_scores_gemma":[0.0004436887,0.00003786081,0.3766514,0.00003430187,0.0000937398,9.700483e-7,0.0001933455,0.6062028,0.000006379371,0.01563753,0.0006003929,0.00009756397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4306263,0.0003483828,0.5682198,0.00004651655,0.00007702986,0.00007746359,0.00003759935,0.000003774845,0.0005630727],"genre_scores_gemma":[0.9797934,0.0001774512,0.01974801,0.00009249729,0.00003534474,0.00000423438,0.00005407106,0.00001433424,0.00008064534],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5491671,"threshold_uncertainty_score":0.6550356,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1233780640120905,"score_gpt":0.315785608030816,"score_spread":0.1924075440187255,"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."}}