{"id":"W3039936924","doi":"10.2139/ssrn.3402471","title":"Cross-Category Product Choice: A Scalable Deep-Learning Model","year":2019,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Consumer Market Behavior and Pricing","field":"Business, Management and Accounting","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Product (mathematics); Computer science; Artificial intelligence; Deep learning; Natural language processing; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001595703,0.00100492,0.001768134,0.0008537995,0.0005262155,0.001206009,0.003298388,0.003050743,0.006908044],"category_scores_gemma":[0.003622056,0.0009616178,0.001449986,0.001282977,0.0006696411,0.002314917,0.001658141,0.003654207,0.001903525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001744257,"about_ca_system_score_gemma":0.001588936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03963001,"about_ca_topic_score_gemma":0.04521695,"domain_scores_codex":[0.9996417,0.00009550205,0.00001555591,0.0001190115,0.00003845799,0.00008968201],"domain_scores_gemma":[0.9983466,0.001059951,0.00008621645,0.0001762409,0.0002059687,0.0001250468],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009066888,0.0009425501,0.006961201,0.0001219594,0.000266257,0.000193858,0.00006576029,0.7973648,0.0008478481,0.00863426,0.01385087,0.1698439],"study_design_scores_gemma":[0.0000116072,0.00001127676,0.0001699421,0.000004007482,0.00000727356,0.000004739302,0.000002947651,0.9973123,0.00004342664,0.002322521,0.0001065079,0.000003456848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4694509,0.003889219,0.499208,0.005415157,0.0006771332,0.0002171838,0.006878546,0.004146805,0.01011698],"genre_scores_gemma":[0.9380728,0.0005243635,0.04387782,0.0007253739,0.0001762409,0.0001326719,0.003575383,0.0001283269,0.01278698],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03963001,"threshold_uncertainty_score":0.07879865,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01041548988401647,"score_gpt":0.2466860610689738,"score_spread":0.2362705711849574,"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."}}