{"id":"W4408256302","doi":"10.5267/j.dsl.2025.1.003","title":"Predicting production costs in procurement logistics: A comparison of OLS regression and neural networks in a Peruvian paper company","year":2025,"lang":"en","type":"article","venue":"Decision Science Letters","topic":"Quality and Supply Management","field":"Business, Management and Accounting","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Procurement; Production (economics); Artificial neural network; Business; Regression analysis; Regression; Operations management; Industrial organization; Operations research; Computer science; Manufacturing engineering; Engineering; Marketing; Artificial intelligence; Statistics; Economics; Machine learning; Mathematics; Microeconomics","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":[0.002111503,0.0001311741,0.0002528449,0.0008408689,0.0001707873,0.000236351,0.0003283498,0.000036514,0.00001035429],"category_scores_gemma":[0.0006590384,0.0001082618,0.0000248439,0.001806413,0.0003041025,0.00105727,0.0003527142,0.0001934996,0.000002202633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001064132,"about_ca_system_score_gemma":0.00001322764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003972081,"about_ca_topic_score_gemma":0.0006680142,"domain_scores_codex":[0.9980562,0.00002945599,0.0005678658,0.0004781816,0.0005649469,0.0003033196],"domain_scores_gemma":[0.9993612,0.0001031199,0.000196037,0.000247404,0.00007956819,0.00001272294],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001106771,0.0001355607,0.897027,0.0001065481,0.000002645112,0.00000581914,0.0002842722,0.03914801,0.002168667,0.001179127,0.001903865,0.05792786],"study_design_scores_gemma":[0.0005193956,0.000009458156,0.5335875,0.0006140519,0.000008354787,3.205464e-7,0.001033499,0.4627949,0.00005062523,0.0003474891,0.0009161968,0.0001181446],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9809213,0.00007578456,0.009861411,0.007654714,0.0005425668,0.0005745994,3.325461e-7,0.00002262095,0.0003467062],"genre_scores_gemma":[0.9966395,0.000005296533,0.0003460436,0.002887403,0.00008297484,0.00002315391,0.000003058965,0.000004302494,0.000008251254],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4236469,"threshold_uncertainty_score":0.4414788,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.036269125606576,"score_gpt":0.3192566997807171,"score_spread":0.2829875741741411,"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."}}