{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00150309,0.0001494279,0.0003868174,0.001885569,0.00002308558,0.00008227963,0.0007865448,0.00005622521,0.0001043952],"category_scores_gemma":[0.0002830348,0.0001353023,0.0001349682,0.001363762,0.000258547,0.001496921,0.0002558476,0.0002184597,0.000007837371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001406154,"about_ca_system_score_gemma":0.0001123844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004108452,"about_ca_topic_score_gemma":0.0000513855,"domain_scores_codex":[0.9963396,0.0001421414,0.001872972,0.0002949452,0.001216718,0.0001336429],"domain_scores_gemma":[0.9971195,0.0001612455,0.001687374,0.000233443,0.0007468968,0.00005157577],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0006744046,0.0001715661,0.2638941,0.00009439942,0.0001149079,0.00001903491,0.0005326435,0.00062987,0.00197608,0.05752645,0.0004502706,0.6739163],"study_design_scores_gemma":[0.02201949,0.001481108,0.4269606,0.003268985,0.0003832801,0.001022061,0.04797826,0.05814386,0.123671,0.06206285,0.2509369,0.002071674],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6975505,0.0001919823,0.275942,0.002302415,0.002672376,0.00143605,0.0000730532,0.00003240713,0.01979917],"genre_scores_gemma":[0.9841243,0.0003433992,0.01522525,0.00006619547,0.0001525722,0.00001813518,0.000008531434,0.000007687539,0.00005392242],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6718446,"threshold_uncertainty_score":0.5517467,"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."}}