{"id":"W4311543603","doi":"10.1016/j.asoc.2022.109924","title":"The choice of scaling technique matters for classification performance","year":2022,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":342,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Scaling; Normalization (sociology); Preprocessor; Pipeline (software); Data mining; Data pre-processing; Range (aeronautics); Machine learning; Artificial intelligence; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006879713,0.001332384,0.001813182,0.001792543,0.0009495445,0.004587837,0.001208418,0.00207702,0.006267045],"category_scores_gemma":[0.04544812,0.0004487346,0.0008379299,0.003621918,0.001084833,0.005252711,0.001172306,0.002131833,0.005119657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003273333,"about_ca_system_score_gemma":0.0009103965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006848201,"about_ca_topic_score_gemma":0.0009640818,"domain_scores_codex":[0.99709,0.0009483534,0.0003657236,0.0006222915,0.0007476455,0.0002259453],"domain_scores_gemma":[0.9843584,0.008913347,0.0005024094,0.002956575,0.002725875,0.0005433771],"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":[0.001149446,0.001009154,0.01328669,0.0008014378,0.0003273692,0.0003374403,0.0004782187,0.01798071,0.1303659,0.006720267,0.0161164,0.811427],"study_design_scores_gemma":[0.0006643573,0.002343073,0.0510213,0.001387964,0.0009043625,0.002427013,0.002393956,0.6374383,0.2021025,0.05889113,0.03982456,0.0006013986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3332424,0.01021037,0.6119822,0.006892423,0.005779434,0.0008338571,0.001155534,0.006207708,0.02369612],"genre_scores_gemma":[0.7379632,0.004535563,0.246617,0.001013797,0.001439367,0.0003063297,0.0009243838,0.001481708,0.005718603],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006879713,"threshold_uncertainty_score":0.03638387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02762515347572305,"score_gpt":0.2739750754989949,"score_spread":0.2463499220232718,"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."}}