{"id":"W2163067442","doi":"10.1109/icdm.2009.118","title":"A New MCA-Based Divisive Hierarchical Algorithm for Clustering Categorical Data","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Categorical variable; Cluster analysis; Computer science; Similarity (geometry); Hierarchical clustering; Data mining; Pattern recognition (psychology); Algorithm; Canopy clustering algorithm; Single-linkage clustering; Subspace topology; Artificial intelligence; Linear subspace; CURE data clustering algorithm; Correlation clustering; Mathematics; Machine learning","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":[0.002844071,0.001089081,0.001705638,0.004326705,0.002123136,0.002008655,0.003530304,0.001564775,0.002645461],"category_scores_gemma":[0.008628754,0.000702721,0.001709836,0.007883797,0.001118036,0.002544518,0.001948764,0.002463199,0.001709409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001729299,"about_ca_system_score_gemma":0.003617902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01308928,"about_ca_topic_score_gemma":0.01551876,"domain_scores_codex":[0.9965888,0.0007815353,0.0002020916,0.000878889,0.001382085,0.0001666082],"domain_scores_gemma":[0.9968038,0.001034059,0.0002407828,0.0004807247,0.001286779,0.0001539018],"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":[0.0001630652,0.0001174293,0.002246686,0.0002788734,0.0002924794,0.0001249478,0.0005943787,0.1082161,0.01141347,0.03059785,0.01484128,0.8311135],"study_design_scores_gemma":[0.00003538268,0.00005270315,0.0007397177,0.0000310579,0.00004082492,0.0002047231,0.0001096694,0.9433341,0.005330708,0.03259683,0.01745638,0.00006788257],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001774337,0.000234224,0.9962897,0.0001261461,0.00006089365,0.0001004157,0.0001296212,0.0006366218,0.0006480192],"genre_scores_gemma":[0.02326791,0.00013027,0.9743699,0.0001194484,0.00008131837,0.0002526843,0.0004240697,0.0001545425,0.001199852],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01308928,"threshold_uncertainty_score":0.02602619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05942537267736089,"score_gpt":0.3551315825387727,"score_spread":0.2957062098614118,"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."}}