{"id":"W3158898498","doi":"10.1287/inte.2020.1055","title":"A Machine Learning-Based System for Predicting Service-Level Failures in Supply Chains","year":2021,"lang":"en","type":"article","venue":"INFORMS Journal on Applied Analytics","topic":"Supply Chain Resilience and Risk Management","field":"Business, Management and Accounting","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Supply chain; Computer science; Service level; Service management; Service (business); Stock (firearms); Risk analysis (engineering); Supply chain management; Operations management; Operations research; Reliability engineering; Business; Engineering; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000864087,0.0003046077,0.0004054702,0.000732048,0.0004217451,0.0007242992,0.0003800332,0.0001187244,0.00008591849],"category_scores_gemma":[0.0001397518,0.0002402637,0.0001832052,0.0010848,0.00002680667,0.0004476022,0.0001276464,0.0005726153,0.00009295291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001916696,"about_ca_system_score_gemma":0.0001236299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001301186,"about_ca_topic_score_gemma":0.0006895226,"domain_scores_codex":[0.997783,0.00000803717,0.0007533388,0.000287439,0.0005952354,0.0005729265],"domain_scores_gemma":[0.9987187,0.0001200889,0.0005404651,0.0002450515,0.0003271949,0.00004849383],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005328731,0.0003594681,0.07355437,0.002019064,0.000241457,0.0003368803,0.0003321165,0.8247986,0.0001521969,0.07954544,0.001859939,0.01626757],"study_design_scores_gemma":[0.004050217,0.00005105173,0.003753979,0.0004809718,0.0001394582,0.00002054262,0.007054566,0.8652311,0.0002566947,0.000684772,0.1177571,0.0005195228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6480567,0.0007603163,0.1655191,0.03497986,0.004445208,0.005779279,0.0001731561,0.001546802,0.1387395],"genre_scores_gemma":[0.9932551,0.00002868705,0.0006287399,0.004503605,0.0009247832,0.00004408385,0.0001165073,0.00004374223,0.0004547719],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3451983,"threshold_uncertainty_score":0.9797668,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02284518305943014,"score_gpt":0.2354543909942878,"score_spread":0.2126092079348577,"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."}}