{"id":"W2982358567","doi":"10.1061/(asce)co.1943-7862.0001736","title":"Machine Learning Algorithms for Construction Projects Delay Risk Prediction","year":2019,"lang":"en","type":"article","venue":"Journal of Construction Engineering and Management","topic":"Construction Project Management and Performance","field":"Decision Sciences","cited_by":310,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Machine learning; Computer science; Artificial intelligence; Decision tree; Bayesian network; Set (abstract data type); Interdependence; Online machine learning; Data mining; Algorithm; Active learning (machine learning)","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":[0.001984447,0.0001696969,0.0002988765,0.0009647034,0.0001624507,0.0001972309,0.0001750778,0.00006428164,0.00008363104],"category_scores_gemma":[0.0002027878,0.0001403035,0.0001213683,0.0005006912,0.00005574685,0.0006616662,0.00006651385,0.0002636863,0.00001117601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005322674,"about_ca_system_score_gemma":0.00002240624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004056686,"about_ca_topic_score_gemma":8.291005e-7,"domain_scores_codex":[0.9980114,0.00005673575,0.0008364982,0.0002721153,0.0006241947,0.0001991004],"domain_scores_gemma":[0.9984612,0.0001833283,0.0007645195,0.0001783676,0.0003315879,0.00008093191],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001620051,0.00002057974,0.04502165,0.0001522573,0.0002693365,0.000005151556,0.0001880786,0.0425467,0.0002014849,0.01259173,0.0004114328,0.8984296],"study_design_scores_gemma":[0.003736141,0.0007746314,0.01132484,0.0001565433,0.00027585,0.001287079,0.002454282,0.4237843,0.0004601708,0.002662799,0.55269,0.0003933276],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.428039,0.0003793261,0.5617484,0.0001899466,0.006468368,0.0008843139,0.00001993451,0.0001006772,0.002170015],"genre_scores_gemma":[0.8512834,0.002657114,0.1435637,0.00002837859,0.0004796138,0.00002811106,0.000007033198,0.00002985618,0.001922813],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8980362,"threshold_uncertainty_score":0.5721411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02207567151945878,"score_gpt":0.2701024369812171,"score_spread":0.2480267654617583,"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."}}