{"id":"W4367693609","doi":"10.1016/j.dajour.2023.100238","title":"A decision support system for classifying supplier selection criteria using machine learning and random forest approach","year":2023,"lang":"en","type":"article","venue":"Decision Analytics Journal","topic":"Supply Chain Resilience and Risk Management","field":"Business, Management and Accounting","cited_by":80,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"","keywords":"Random forest; Computer science; Critical success factor; General partnership; Supply chain; Feature selection; Classifier (UML); Machine learning; Selection (genetic algorithm); Artificial intelligence; Process management; Knowledge management; Business; Marketing","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":[0.003751724,0.001233932,0.001231446,0.004954056,0.0009012888,0.001661586,0.001261998,0.001254557,0.004621468],"category_scores_gemma":[0.009147368,0.0003756042,0.001238097,0.002215331,0.000231953,0.001497998,0.0007167008,0.0008130009,0.002057684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001052978,"about_ca_system_score_gemma":0.001710085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009357176,"about_ca_topic_score_gemma":0.009406319,"domain_scores_codex":[0.9984035,0.0004057331,0.0002438896,0.0002733548,0.0005121877,0.0001613776],"domain_scores_gemma":[0.9953653,0.002326263,0.0003984613,0.0001927715,0.001565589,0.000151696],"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":[0.001089008,0.0008818335,0.02216027,0.0005518584,0.0002133225,0.0006533611,0.0003221839,0.09911715,0.008184643,0.004020232,0.01719595,0.8456102],"study_design_scores_gemma":[0.0001115143,0.000276096,0.00436742,0.00009826338,0.0001042821,0.0001862854,0.0001458765,0.9819549,0.004874874,0.004364139,0.003458932,0.00005739578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1048625,0.0003954796,0.8708904,0.0008258711,0.0001233065,0.001138075,0.00288906,0.01494592,0.003929361],"genre_scores_gemma":[0.407299,0.000205615,0.5866274,0.0001814941,0.00007418989,0.0007334411,0.003257242,0.000120441,0.00150116],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009357176,"threshold_uncertainty_score":0.01984125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04025731035290513,"score_gpt":0.3094333304782187,"score_spread":0.2691760201253136,"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."}}