{"id":"W4254786677","doi":"10.4018/978-1-59140-557-3.ch056","title":"Data Mining with Incomplete Data","year":2005,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Missing data; Ambiguity; Survey data collection; Computer science; Data mining; Data set; Data science; Artificial intelligence; Statistics; 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":[0.02422695,0.002185808,0.004260969,0.008810535,0.002131128,0.008495379,0.006298503,0.003079063,0.003928753],"category_scores_gemma":[0.0795491,0.001819883,0.00516643,0.01413813,0.00295079,0.01337282,0.008944872,0.00526582,0.003264409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001427058,"about_ca_system_score_gemma":0.003214721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001094236,"about_ca_topic_score_gemma":0.001261772,"domain_scores_codex":[0.9668185,0.01522398,0.00388867,0.005947318,0.007562418,0.0005591911],"domain_scores_gemma":[0.9292134,0.04723025,0.003932132,0.01522603,0.003852431,0.0005457342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002899477,0.0003478294,0.01015839,0.008242946,0.001805571,0.001602254,0.002302741,0.04321602,0.001927706,0.1783194,0.04290136,0.7088858],"study_design_scores_gemma":[0.00008965834,0.0002080468,0.002277768,0.00234245,0.0004254307,0.002149176,0.001245389,0.1759314,0.004749846,0.6628361,0.1475964,0.000148388],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002933752,0.006117238,0.9817975,0.002334476,0.0003005632,0.0004504999,0.002573656,0.0007422224,0.002750124],"genre_scores_gemma":[0.04013485,0.008694775,0.9398875,0.001053268,0.0007024168,0.0009806888,0.006297673,0.0001618275,0.002086947],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02422695,"threshold_uncertainty_score":0.1281259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08128089344225493,"score_gpt":0.2934700909831993,"score_spread":0.2121891975409444,"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."}}