{"id":"W2765831835","doi":"","title":"A Hybrid Data Mining Approach for Product Complexity Analysis.","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Product Development and Customization","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Hierarchical clustering; Data mining; Cluster analysis; Computer science; Product (mathematics); Bayesian probability; Hellinger distance; Similarity (geometry); Quality (philosophy); Measure (data warehouse); Machine learning; Artificial intelligence; Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004899412,0.0001508623,0.0002271323,0.0002592647,0.0008858914,0.0003712101,0.001362531,0.0000264425,0.00004537305],"category_scores_gemma":[0.0002303763,0.0001628065,0.0000808302,0.0003990504,0.0001188931,0.00243405,0.0007300538,0.00005850814,0.00003226711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002706483,"about_ca_system_score_gemma":0.00002797634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001439912,"about_ca_topic_score_gemma":0.00007113091,"domain_scores_codex":[0.9987699,0.000007811494,0.0001300365,0.0007779152,0.00006386043,0.0002504956],"domain_scores_gemma":[0.9980224,0.00001254893,0.0003266612,0.001456349,0.0001665699,0.00001551939],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005443472,0.0005548563,0.692588,0.0005089173,0.001948227,0.00006003272,0.00009543178,0.019209,0.0001067581,0.2382038,0.03907967,0.007100876],"study_design_scores_gemma":[0.0009671425,0.000003786365,0.0548168,0.000008396579,0.001064211,5.812058e-7,0.0001098945,0.9233016,0.00003837537,0.004725008,0.0145448,0.0004193471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7021654,0.00002382623,0.2668552,0.0004500497,0.0003528004,0.0007235621,0.00003520396,0.0002310226,0.02916296],"genre_scores_gemma":[0.9940645,0.000004098458,0.002666195,0.0001284308,0.000498591,0.000001111237,0.0009285108,0.00001429459,0.001694287],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9040927,"threshold_uncertainty_score":0.681365,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2181782444093562,"score_gpt":0.2125915665319987,"score_spread":0.005586677877357477,"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."}}