{"id":"W4285021604","doi":"10.1016/j.jbusres.2022.07.004","title":"The usefulness of socio-demographic variables in predicting purchase decisions: Evidence from machine learning procedures","year":2022,"lang":"en","type":"article","venue":"Journal of Business Research","topic":"Consumer Market Behavior and Pricing","field":"Business, Management and Accounting","cited_by":29,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"Australian Research Council; Social Sciences and Humanities Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Predictive power; Logistic regression; Predictability; Sample (material); Product (mathematics); Demographics; Computer science; Econometrics; Ordered logit; Lasso (programming language); Statistics; Marketing; Machine learning; Mathematics; Demography; Business","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":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.01199178,0.0001504223,0.0003488277,0.001338988,0.001387418,0.000373232,0.001068061,0.00005237735,0.0003081177],"category_scores_gemma":[0.0168908,0.0001103854,0.0001203032,0.004076257,0.0001878866,0.001135254,0.001075145,0.001592793,0.00000237464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008354745,"about_ca_system_score_gemma":0.0003913941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003750192,"about_ca_topic_score_gemma":0.000481608,"domain_scores_codex":[0.9961284,0.0003794427,0.0009111468,0.0002329888,0.001896274,0.0004517846],"domain_scores_gemma":[0.9927339,0.004140653,0.0007351117,0.0002638734,0.002100928,0.00002552244],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007778869,0.0001611385,0.9590743,0.0001399831,0.00004169873,0.000102938,0.000352893,0.003500647,0.002667313,0.00007740671,0.0003719565,0.03273184],"study_design_scores_gemma":[0.001240461,0.00005485132,0.9688951,0.001561931,0.00008926041,0.00004000833,0.006492491,0.01018472,0.00007219495,0.003893524,0.00725176,0.000223694],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9904682,0.006270375,0.0002675443,0.00228754,0.0003413251,0.0002387275,0.000003844965,0.00001452189,0.0001079183],"genre_scores_gemma":[0.9982433,0.001108598,0.0001119132,0.00003852202,0.0003742909,0.00003521637,0.000004374793,0.00002879089,0.00005498087],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03250815,"threshold_uncertainty_score":0.9999126,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1084331461864188,"score_gpt":0.3326524469390205,"score_spread":0.2242193007526017,"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."}}