{"id":"W4411436346","doi":"10.1007/978-3-031-87496-3_12","title":"Is Expert-Labeled Data Worth the Cost? Exploring Active and Semi-supervised Learning Across Imbalance Scenarios in Financial Crime Detection","year":2025,"lang":"en","type":"book-chapter","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 Ottawa","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Supervised learning; Finance; Labeled data; Data science; Artificial neural network; Economics","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":[0.01223055,0.001142183,0.001955477,0.001428526,0.0006972794,0.003622405,0.003035316,0.002670187,0.002180885],"category_scores_gemma":[0.03022186,0.0006888486,0.001017467,0.001605266,0.001860137,0.009792075,0.002332822,0.003372561,0.00068699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009269936,"about_ca_system_score_gemma":0.0008998377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002314523,"about_ca_topic_score_gemma":0.004404827,"domain_scores_codex":[0.9963313,0.002189713,0.000138857,0.0006632152,0.0004450048,0.0002319435],"domain_scores_gemma":[0.9566887,0.03811848,0.001153553,0.001889106,0.001674867,0.0004752373],"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":[0.001041441,0.000966544,0.02173947,0.0005434899,0.000370129,0.0002170884,0.0008997186,0.2232201,0.00210251,0.03919952,0.02043777,0.6892622],"study_design_scores_gemma":[0.00002061501,0.00008746807,0.001619347,0.00005531139,0.00003499155,0.00006439492,0.0002210678,0.9235344,0.0006776758,0.07243591,0.001231138,0.0000177295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1899774,0.004491979,0.7883034,0.007112259,0.0003072787,0.000142818,0.0007978812,0.000998924,0.007868042],"genre_scores_gemma":[0.8593157,0.0008118587,0.1336942,0.0006740161,0.0005432466,0.0000984026,0.00119707,0.0002230356,0.003442565],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01223055,"threshold_uncertainty_score":0.06468207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05898058754057987,"score_gpt":0.3038318852418694,"score_spread":0.2448512977012895,"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."}}