{"id":"W3116827229","doi":"10.1007/978-3-030-71158-0_8","title":"Cost-Sensitive Semi-supervised Classification for Fraud Applications","year":2021,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Bidding; Scarcity; Machine learning; Labeled data; Artificial intelligence; Domain (mathematical analysis); Data mining; Business; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001272407,0.0004853526,0.0005364852,0.0007049759,0.0003908326,0.001506239,0.004815486,0.0004530985,0.000003307882],"category_scores_gemma":[0.0003397833,0.0005106222,0.0001682507,0.002412028,0.000519861,0.0008912623,0.002923243,0.0009070012,0.00001111212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006341061,"about_ca_system_score_gemma":0.00142102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003071331,"about_ca_topic_score_gemma":0.00003823834,"domain_scores_codex":[0.9949814,0.0001527633,0.0007095809,0.002636514,0.0007891029,0.0007306029],"domain_scores_gemma":[0.9938809,0.0008015102,0.0004568118,0.003507114,0.001168417,0.0001852923],"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":[0.000005491378,0.000178909,0.0001872827,0.0001341426,0.00001389871,0.000006228737,0.001552369,0.01550747,0.01231276,0.005017243,0.00008501108,0.9649992],"study_design_scores_gemma":[0.0002166214,0.00003830107,0.002242751,0.0001701228,0.000008246116,0.00001535673,0.000003941255,0.9036957,0.07006491,0.02243707,0.0005514204,0.000555549],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005363378,0.0001533832,0.9913399,0.003271866,0.00114721,0.002812366,0.00007329565,0.0006333239,0.0000323395],"genre_scores_gemma":[0.4080568,0.00004059565,0.5890872,0.001118149,0.0002235475,0.001272522,0.0001812063,0.00001872465,0.000001223166],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9644436,"threshold_uncertainty_score":0.9997345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05000733513116704,"score_gpt":0.318667674835975,"score_spread":0.268660339704808,"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."}}