{"id":"W4417200992","doi":"10.1108/bpmj-07-2025-1194","title":"Improving business process performance in SMEs through predictive modeling: a comparative study of statistical and machine learning models","year":2025,"lang":"en","type":"article","venue":"Business Process Management Journal","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"MacEwan University","funders":"","keywords":"Interpretability; Workflow; Demand forecasting; Business process management; Business process; Business intelligence; Process (computing); Scalability; Process modeling; Autoregressive integrated moving average","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":[0.001481479,0.0002457589,0.0005233944,0.0006209882,0.0004372194,0.0003171971,0.0006983754,0.00005455346,0.00001150731],"category_scores_gemma":[0.0003303457,0.000187746,0.00002363146,0.003017664,0.000128433,0.001096024,0.0003291224,0.0004146737,8.119489e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005006462,"about_ca_system_score_gemma":0.0001280335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000886585,"about_ca_topic_score_gemma":0.00003959438,"domain_scores_codex":[0.9970614,0.000110414,0.001069613,0.0005516306,0.0009078599,0.0002990276],"domain_scores_gemma":[0.9971936,0.0001720185,0.0005624723,0.000247771,0.001773363,0.00005072829],"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":[0.0003861914,0.0009322881,0.0286199,0.0005564859,0.00006879931,0.00001467736,0.005438054,0.9271113,0.000005419005,0.004470591,0.0000288565,0.03236743],"study_design_scores_gemma":[0.001005641,0.0001135556,0.01314592,0.0003301667,0.00005831051,0.00001198343,0.01018729,0.8641151,0.00001588175,0.1108406,0.00001567986,0.0001598433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4625861,0.0001208629,0.5346764,0.0001204917,0.00003744811,0.0005576701,0.000004877375,0.00003511607,0.001861008],"genre_scores_gemma":[0.9949455,0.0001383887,0.004577708,0.00001999994,0.00002126539,0.000148544,0.000004279373,0.00001335106,0.0001309458],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5323594,"threshold_uncertainty_score":0.765606,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1471707033169902,"score_gpt":0.396491394192856,"score_spread":0.2493206908758657,"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."}}