{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001193235,0.0001049573,0.0001246899,0.00007355097,0.0008891475,0.0000578061,0.00163435,0.00002587678,8.808482e-7],"category_scores_gemma":[0.00003571409,0.00009613101,0.00004159959,0.0003530525,0.00005892666,0.00009622137,0.0008907455,0.0001792934,0.000001212547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007118226,"about_ca_system_score_gemma":0.00004474202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007976309,"about_ca_topic_score_gemma":3.386439e-7,"domain_scores_codex":[0.9988347,0.00003695211,0.0003158299,0.0003125432,0.0002457799,0.0002542036],"domain_scores_gemma":[0.9982278,0.0007558252,0.0002956638,0.0006488034,0.00004760211,0.00002433923],"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":[0.00002523976,0.00008649071,0.0009688889,0.0001169543,0.00003192222,4.242522e-7,0.001149266,0.002334679,0.09248815,0.153286,0.00688312,0.7426288],"study_design_scores_gemma":[0.0003406462,0.0001445792,0.00249973,0.00004743952,0.0000118643,0.00001473234,0.0003088032,0.8704174,0.07944652,0.005032215,0.04134708,0.0003889468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01230407,0.00001416794,0.9855074,0.0005731006,0.0001127529,0.0005975346,0.000004902454,0.0004107136,0.0004753839],"genre_scores_gemma":[0.6887048,0.000001053063,0.3107503,0.0002418806,0.00002337879,0.0002515841,0.000008413526,0.00001068338,0.000007905507],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8680828,"threshold_uncertainty_score":0.6838693,"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."}}