{"id":"W3011988108","doi":"10.1080/15623599.2020.1738205","title":"Application of knowledge discovery in database (KDD) techniques in cost overrun of construction projects","year":2020,"lang":"en","type":"article","venue":"International Journal of Construction Management","topic":"Construction Project Management and Performance","field":"Decision Sciences","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Knowledge extraction; Data mining; Cluster analysis; Cost overrun; Data science; Rough set; Engineering; Machine learning; Construction industry; Construction engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006563149,0.0007954885,0.001351001,0.01079059,0.001049512,0.002512054,0.001631368,0.0009593899,0.0006334767],"category_scores_gemma":[0.02126165,0.0005277699,0.001335138,0.01084666,0.0005513676,0.002350273,0.001541394,0.001109912,0.0002104514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001577183,"about_ca_system_score_gemma":0.002584067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01627884,"about_ca_topic_score_gemma":0.0134731,"domain_scores_codex":[0.9950113,0.001612753,0.0006837561,0.0006924458,0.001759231,0.0002405231],"domain_scores_gemma":[0.9839029,0.01094688,0.001649795,0.001047656,0.002274903,0.0001778097],"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":[0.0002488926,0.000905477,0.1838854,0.001142881,0.0009099022,0.001002732,0.0009801892,0.2314219,0.001343695,0.01107276,0.005540368,0.5615457],"study_design_scores_gemma":[0.00005136475,0.0002481366,0.05076025,0.0002727564,0.0003321984,0.0006737827,0.0009390751,0.9167174,0.003330152,0.01862382,0.00793226,0.0001189053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4416653,0.005821366,0.5345669,0.002892757,0.0002834506,0.0009110736,0.003073211,0.001079943,0.009705934],"genre_scores_gemma":[0.8459971,0.002105516,0.1497328,0.0001353321,0.00004805126,0.0002217553,0.001176041,0.0000247986,0.0005586456],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01627884,"threshold_uncertainty_score":0.03470963,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0634758657941571,"score_gpt":0.3759332557420735,"score_spread":0.3124573899479164,"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."}}