{"id":"W7114809687","doi":"10.5267/j.jpm.2025.10.003","title":"Enhancing project financial performance prediction: An explainable machine learning framework integrating frontier efficiency and super learner","year":2025,"lang":"en","type":"article","venue":"Journal of Project Management","topic":"Efficiency Analysis Using DEA","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Prince Sattam bin Abdulaziz University","keywords":"Categorical variable; Data envelopment analysis; Leverage (statistics); Weighting; Robustness (evolution); Random forest; Estimator; Boosting (machine learning); Gradient boosting; Support vector machine","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":[0.008873766,0.0002636625,0.0005501591,0.00198807,0.0007675101,0.0006875619,0.0007973681,0.0001201887,0.0000678408],"category_scores_gemma":[0.003077817,0.0001841843,0.0001839122,0.00272159,0.0001212037,0.001200685,0.0003274218,0.0009113807,0.000008244494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001679162,"about_ca_system_score_gemma":0.0002912914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005681324,"about_ca_topic_score_gemma":0.00002870351,"domain_scores_codex":[0.9954842,0.0005141429,0.001452658,0.000563665,0.001549389,0.0004359277],"domain_scores_gemma":[0.9978393,0.0003859706,0.0007219041,0.0004348745,0.0005523303,0.00006565858],"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":[0.001402515,0.002139129,0.3356604,0.0008782811,0.000848359,0.0005638181,0.03704319,0.07356107,0.001437444,0.01734997,0.02105634,0.5080595],"study_design_scores_gemma":[0.00313607,0.003995784,0.03662982,0.003119071,0.0009188626,0.0002219468,0.04835159,0.6542062,0.001911258,0.006560262,0.2397147,0.001234403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6082153,0.001385989,0.3806882,0.0003388998,0.001060348,0.0004969501,0.000002014662,0.00005161975,0.007760641],"genre_scores_gemma":[0.9598556,0.0003224545,0.03056789,0.0002130581,0.0002337511,0.00001612695,0.000001745669,0.0000170512,0.008772296],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5806451,"threshold_uncertainty_score":0.7510819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03000783713424258,"score_gpt":0.3436947384547502,"score_spread":0.3136869013205076,"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."}}