{"id":"W3014694269","doi":"10.1002/for.2689","title":"Predictive modeling of consumer color preference: Using retail data and merchandise images","year":2020,"lang":"en","type":"article","venue":"Journal of Forecasting","topic":"Color perception and design","field":"Psychology","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Multinomial logistic regression; Popularity; Sample (material); Preference; Consumer behaviour; Product (mathematics); Computer science; Order (exchange); Function (biology); Advertising; Econometrics; Business; Economics; Mathematics; Machine learning; Microeconomics; Psychology","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":[0.0005353421,0.00009407497,0.0002794359,0.00008160342,0.00006264786,0.00002175934,0.0002002083,0.00006479723,0.0003328982],"category_scores_gemma":[0.0004096718,0.00007961806,0.00004431676,0.0001187296,0.00007556556,0.0002469952,0.0001166137,0.000248148,0.000002331907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001685188,"about_ca_system_score_gemma":0.00007277516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001585084,"about_ca_topic_score_gemma":0.000001866388,"domain_scores_codex":[0.9988949,0.0001103015,0.0005084241,0.0001670987,0.0001788841,0.000140345],"domain_scores_gemma":[0.9989261,0.0001432407,0.000440968,0.000137382,0.0002223938,0.0001299115],"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":[0.02471812,0.001133339,0.1450045,0.001225319,0.003668417,0.0009891783,0.1857225,0.07294062,0.1938079,0.0005415078,0.02388758,0.3463609],"study_design_scores_gemma":[0.001112751,0.0004935749,0.0008871891,0.0001494757,0.0001862462,0.0002618431,0.004544826,0.9918905,0.0001113841,0.00009741759,0.00016513,0.00009967636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9279376,0.0008559816,0.06938046,0.000155818,0.0001689946,0.0001101901,0.00006116053,0.000009189377,0.001320615],"genre_scores_gemma":[0.9929537,0.00005325598,0.006710985,0.00007678651,0.0001675151,6.458135e-7,0.000002840343,0.00001139263,0.00002288479],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9189498,"threshold_uncertainty_score":0.3645002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4915125811581008,"score_gpt":0.3769196897903212,"score_spread":0.1145928913677796,"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."}}