{"id":"W4286630276","doi":"10.5198/jtlu.2022.1905","title":"A prototype machine learning residential land-use classifier using housing market dynamics","year":2022,"lang":"en","type":"article","venue":"Journal of Transport and Land Use","topic":"Housing Market and Economics","field":"Economics, Econometrics and Finance","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Real estate; Land use; Computer science; Workflow; Microsimulation; Classifier (UML); Digitization; Predictive power; Machine learning; Data mining; Data science; Artificial intelligence; Transport engineering; Database; Engineering; Business; Civil 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":[0.0009968992,0.0001540559,0.0004621586,0.0003115016,0.0003466265,0.0001569118,0.0001329269,0.00007225754,0.0004756755],"category_scores_gemma":[0.00003559812,0.0001623247,0.0001654435,0.0001392364,0.00003468144,0.0005974803,0.0000348684,0.0005355133,0.00000149058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001366793,"about_ca_system_score_gemma":0.00005093659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008378964,"about_ca_topic_score_gemma":0.0006087486,"domain_scores_codex":[0.9986826,0.00004044779,0.0007587369,0.0002017675,0.00006707086,0.0002493822],"domain_scores_gemma":[0.9990568,0.0000581321,0.000622859,0.0001196729,0.00003220491,0.0001103864],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007461115,0.00006140329,0.994581,0.00003196047,0.00008241957,0.0001087303,0.0002546241,0.003224343,0.000005136483,0.0001575719,0.0000765626,0.0006701286],"study_design_scores_gemma":[0.004129246,0.0006451473,0.5584337,0.00009119371,0.000173455,0.000507268,0.0001900991,0.2817039,0.000004398412,0.001212298,0.1521024,0.0008069174],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9961753,0.0004003145,0.001656746,0.0001214877,0.0004950901,0.0001406247,0.0001082721,0.00001428362,0.0008879074],"genre_scores_gemma":[0.9973222,0.0006738481,0.00116086,0.00007054973,0.0001596643,0.000002574599,0.00002251747,0.00004021023,0.0005475927],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4361473,"threshold_uncertainty_score":0.6619409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03462644251488398,"score_gpt":0.217028082320177,"score_spread":0.182401639805293,"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."}}