{"id":"W6945027598","doi":"10.25384/sage.22633946","title":"Supplemental Material - Using machine learning to identify spatial market segments. A reproducible study of major Spanish marketssj-pdf-1-epb-10.1177/2399808323116695","year":2023,"lang":"en","type":"article","venue":"Sage Journals Data","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Analytics; Deep learning; Spatial analysis; Big data; Market segmentation; Order (exchange)","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":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01206446,0.000237418,0.0005000427,0.000488886,0.001352818,0.000538722,0.001406886,0.00009236084,0.1685193],"category_scores_gemma":[0.001581205,0.0002482503,0.0001158489,0.001449368,0.0001176762,0.0007272359,0.001054227,0.0003180066,0.0002715956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001893605,"about_ca_system_score_gemma":0.0002612465,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.06647571,"about_ca_topic_score_gemma":0.06143238,"domain_scores_codex":[0.9943242,0.001770336,0.001010103,0.0009257321,0.001346325,0.0006233037],"domain_scores_gemma":[0.9974756,0.000209067,0.0004960396,0.001357029,0.0001848707,0.0002773739],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002029139,0.005185226,0.6044837,0.0004147196,0.003024829,0.000591579,0.06863532,0.002479029,0.07364949,0.00000655786,0.1075051,0.1319953],"study_design_scores_gemma":[0.01168443,0.002148271,0.478179,0.002489615,0.00378218,0.00004159616,0.3061858,0.04686753,0.005886781,0.0008685289,0.1382511,0.00361515],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9937804,0.0001445055,0.0005516396,0.0008532958,0.0005865379,0.0009604451,0.002453563,0.00009978454,0.000569778],"genre_scores_gemma":[0.9919946,0.0002526552,0.0003435783,0.00005980293,0.0008441685,0.00002100211,0.001052826,0.00003609426,0.005395295],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2375505,"threshold_uncertainty_score":0.999997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07896938562041816,"score_gpt":0.4015546907557017,"score_spread":0.3225853051352835,"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."}}