{"id":"W3013330736","doi":"10.1177/1536867x20909688","title":"The random forest algorithm for statistical learning","year":2020,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Financial Distress and Bankruptcy Prediction","field":"Business, Management and Accounting","cited_by":1264,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Random forest; Computer science; Key (lock); Artificial intelligence; Credit card; Machine learning; Algorithm; Statistical learning; World Wide Web","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":[0.008934176,0.002584404,0.002938435,0.004837369,0.001307264,0.003119014,0.003304664,0.00247918,0.01300221],"category_scores_gemma":[0.02266626,0.001431938,0.00302177,0.005932877,0.001556732,0.003977191,0.002990363,0.005373239,0.01755184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001252376,"about_ca_system_score_gemma":0.003468168,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004526564,"about_ca_topic_score_gemma":0.005170436,"domain_scores_codex":[0.9914981,0.00363473,0.0005779433,0.001322653,0.002661731,0.000304777],"domain_scores_gemma":[0.9909278,0.005618379,0.0005036607,0.00133393,0.001418923,0.0001972808],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001035217,0.00008831872,0.00124858,0.0007421238,0.0004555185,0.0001599874,0.0001367519,0.09509333,0.0009190621,0.1131233,0.1152525,0.672677],"study_design_scores_gemma":[0.0001484068,0.00008000566,0.0006377196,0.0003279723,0.0001015798,0.0003947745,0.00004848768,0.448419,0.001407949,0.3751241,0.1731771,0.0001329416],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002893021,0.001430967,0.991581,0.0003725657,0.0002174106,0.0001429111,0.0006534031,0.003442192,0.001870157],"genre_scores_gemma":[0.009788561,0.001632038,0.9808241,0.0003196044,0.0004164077,0.0008287277,0.002295014,0.0008960944,0.00299957],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01300221,"threshold_uncertainty_score":0.04724896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03533706308133225,"score_gpt":0.2758883826175839,"score_spread":0.2405513195362517,"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."}}