{"id":"W2072065544","doi":"10.1145/1923947.1923983","title":"An introduction to data mining and predictive analytics","year":2010,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"IBM (Canada)","funders":"","keywords":"Computer science; Analytics; Data science; Process (computing); Data mining; Predictive analytics; Data analysis; Artificial intelligence","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":[0.00390797,0.001716118,0.00230328,0.004221709,0.000877006,0.005906862,0.002561027,0.002884564,0.01178939],"category_scores_gemma":[0.009153239,0.000845647,0.001552395,0.009350381,0.003146725,0.008853186,0.002361092,0.005992571,0.008866878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001251949,"about_ca_system_score_gemma":0.002099658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001091821,"about_ca_topic_score_gemma":0.001090062,"domain_scores_codex":[0.9953122,0.00114751,0.0005456802,0.0007565074,0.002102097,0.0001358843],"domain_scores_gemma":[0.9913943,0.006616007,0.0002729577,0.0007941238,0.0006980959,0.000224375],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007868393,0.0001154933,0.001199887,0.003395307,0.0001870286,0.0003466631,0.0004756552,0.004358078,0.001295889,0.3115453,0.1577555,0.5192465],"study_design_scores_gemma":[0.00001902548,0.00006401831,0.000576211,0.000815622,0.0000306354,0.0005710768,0.0001307361,0.005969284,0.0003950567,0.3249,0.6664705,0.0000577957],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.001428971,0.3323549,0.5760359,0.02983214,0.009755742,0.000377225,0.002911228,0.002359781,0.04494417],"genre_scores_gemma":[0.03153799,0.3310577,0.5679126,0.01282973,0.02055968,0.001047734,0.003505815,0.0004822351,0.03106652],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01178939,"threshold_uncertainty_score":0.03943944,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02519771867409121,"score_gpt":0.298142209585086,"score_spread":0.2729444909109948,"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."}}