{"id":"W106071789","doi":"10.4018/978-1-60566-010-3.ch082","title":"Data Mining with Incomplete Data","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Missing data; Data mining; Ambiguity; Computer science; Survey data collection; Data set; Set (abstract data type); Data science; Knowledge extraction; Statistics; Artificial intelligence; Machine learning; 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":[0.02390024,0.00206825,0.004129612,0.009240178,0.00198402,0.008623335,0.006364391,0.002952256,0.004697737],"category_scores_gemma":[0.07090078,0.001568609,0.004669619,0.01570429,0.002928711,0.01328802,0.008592636,0.005044933,0.003780779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001616473,"about_ca_system_score_gemma":0.003657581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001090429,"about_ca_topic_score_gemma":0.001228359,"domain_scores_codex":[0.9658685,0.01534531,0.004261836,0.005700069,0.008278206,0.000546087],"domain_scores_gemma":[0.9303494,0.0460277,0.003824746,0.01498515,0.004291911,0.000521037],"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":[0.0002268676,0.0002978327,0.008210179,0.008760084,0.001389981,0.001285163,0.002261266,0.02770931,0.001561742,0.1836888,0.04631329,0.7182954],"study_design_scores_gemma":[0.00008625888,0.0002004141,0.002324803,0.003261429,0.0003901853,0.00231428,0.001416872,0.1144525,0.004374724,0.6233043,0.2477146,0.0001595636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003126582,0.01030063,0.972323,0.003405925,0.0004158652,0.0006702606,0.003834919,0.0009286463,0.004994261],"genre_scores_gemma":[0.04333664,0.01369964,0.9270121,0.001597239,0.0008977717,0.001399446,0.008669161,0.000199931,0.003187976],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02390024,"threshold_uncertainty_score":0.1263981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07953766576169785,"score_gpt":0.2923643524653435,"score_spread":0.2128266867036457,"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."}}