{"id":"W2898284823","doi":"10.3390/jrfm11040070","title":"Identification of Core Suppliers Based on E-Invoice Data Using Supervised Machine Learning","year":2018,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Purchasing; Weighting; Computer science; Invoice; Segmentation; Identification (biology); Artificial intelligence; Core (optical fiber); Data mining; Machine learning; Profit (economics); Operations management; Engineering; Database","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001091095,0.00008346185,0.0001517249,0.0002603448,0.0001378187,0.00006205802,0.0008614766,0.00003326068,0.000003808786],"category_scores_gemma":[0.0001635782,0.00007470421,0.0000283314,0.0002987316,0.0000680049,0.0004205663,0.0002498372,0.0001487169,0.000001982042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003358685,"about_ca_system_score_gemma":0.000033472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001718478,"about_ca_topic_score_gemma":0.000004227662,"domain_scores_codex":[0.9989039,0.00005761911,0.0004316311,0.0002041178,0.0002955146,0.0001072307],"domain_scores_gemma":[0.9985811,0.00004978968,0.0006048395,0.0005755604,0.0001495796,0.00003919037],"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":[0.0003414941,0.0004461683,0.02366273,0.0001991261,0.00004419907,0.00003898729,0.0009916564,0.00101188,0.01199017,0.03982442,0.003338608,0.9181105],"study_design_scores_gemma":[0.0009885265,0.0004542519,0.04751923,0.0001529086,0.00007813397,0.000008036364,0.0000727091,0.913682,0.00671545,0.002515486,0.02761348,0.0001997473],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02876917,0.00004862496,0.9706789,0.00008926056,0.000186709,0.0001019939,0.00003054749,0.00001955405,0.00007522464],"genre_scores_gemma":[0.9000928,0.0002616774,0.09945145,0.00008166268,0.00007985259,9.282778e-7,0.00001209952,0.000005489389,0.00001397687],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9179108,"threshold_uncertainty_score":0.3046349,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03543907226868737,"score_gpt":0.2829890724060541,"score_spread":0.2475500001373668,"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."}}