{"id":"W7116437156","doi":"10.2139/ssrn.5941658","title":"Machine Learning for Earnings Forecasting -US and International Evidence","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Auditing, Earnings Management, Governance","field":"Business, Management and Accounting","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Earnings; Extant taxon; Gradient boosting; Boosting (machine learning); Sample (material); Cash flow; Flexibility (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":[0.008798554,0.0008700541,0.000933731,0.002608606,0.0005535231,0.003013162,0.0009050248,0.001083107,0.008990967],"category_scores_gemma":[0.02381077,0.0002240696,0.0009282508,0.004744371,0.001036747,0.002970978,0.0009119905,0.002618482,0.001863057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008568758,"about_ca_system_score_gemma":0.001197095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01328931,"about_ca_topic_score_gemma":0.007720955,"domain_scores_codex":[0.9979578,0.0009669931,0.0001592069,0.0002510986,0.0004800108,0.0001849101],"domain_scores_gemma":[0.9635364,0.02842907,0.00267646,0.00185346,0.003008873,0.0004958332],"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":[0.002146695,0.0008659473,0.2127509,0.00138672,0.001991034,0.0004246779,0.0002522871,0.05963871,0.0003497166,0.03751787,0.08565573,0.5970196],"study_design_scores_gemma":[0.0009125001,0.001149547,0.3235418,0.005541283,0.003508244,0.0003319293,0.002334264,0.27953,0.004130364,0.2468406,0.1319035,0.0002760861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4781932,0.3383563,0.02865062,0.06638987,0.002786696,0.0000760529,0.00692927,0.0005510232,0.0780669],"genre_scores_gemma":[0.9423468,0.04341264,0.004197658,0.0009424891,0.001322946,0.00001879323,0.002943171,0.00006310875,0.00475238],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01328931,"threshold_uncertainty_score":0.04653174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01992685134511745,"score_gpt":0.2505787546438684,"score_spread":0.2306519032987509,"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."}}