{"id":"W3137652598","doi":"10.37394/23205.2020.19.22","title":"Data Level Approach for Multiclass Imbalance Financial Data","year":2020,"lang":"en","type":"article","venue":"WSEAS TRANSACTIONS ON COMPUTERS","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Oversampling; Artificial intelligence; Resampling; Computer science; Naive Bayes classifier; Machine learning; Decision tree; Logistic regression; Random forest; Classifier (UML); Overfitting; C4.5 algorithm; Support vector machine; Data mining; Artificial neural network; Bandwidth (computing)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0003129435,0.0002486517,0.0002654514,0.00009540708,0.0002726087,0.0002419863,0.007626014,0.0001022308,0.000002914667],"category_scores_gemma":[0.00008540531,0.000261088,0.00006380454,0.0005446104,0.00008471946,0.001590785,0.0002553771,0.000289706,0.0000223535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000540943,"about_ca_system_score_gemma":0.0002053603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001008569,"about_ca_topic_score_gemma":0.00000502782,"domain_scores_codex":[0.9973543,0.00007401056,0.0003603618,0.001483275,0.0003540286,0.0003740619],"domain_scores_gemma":[0.9952707,0.0002052177,0.0001263765,0.004082572,0.00009657666,0.0002185924],"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":[0.0001997187,0.001160178,0.00004164072,0.0002413868,0.0001550223,0.00001198269,0.0005908444,0.01276369,0.001449088,0.01639581,0.2461103,0.7208803],"study_design_scores_gemma":[0.0006156806,0.00009736947,0.0002499892,0.0000153152,0.00001620942,0.000005372975,0.000009008109,0.939724,0.0009353794,0.00008721235,0.05795787,0.000286596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001027352,0.00002517482,0.9876485,0.005081265,0.0003967576,0.0006820606,0.005203651,0.0008458855,0.0001063946],"genre_scores_gemma":[0.11327,0.00002094191,0.8817882,0.003077802,0.0001595416,0.00007705583,0.001547892,0.00002462398,0.00003395489],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9269603,"threshold_uncertainty_score":0.9999841,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2447687294647022,"score_gpt":0.3246120027703148,"score_spread":0.07984327330561258,"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."}}