{"id":"W4365807313","doi":"10.2139/ssrn.4404772","title":"Machine Learning for Economics Research: When What and How?","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Bank of Canada","funders":"","keywords":"Economics education; Economics; Computer science; Artificial intelligence; Mathematics education; Data science; Machine learning; Psychology","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":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0822503,0.0001389332,0.0002765084,0.00082079,0.0008937378,0.001571964,0.0007216522,0.00008938456,0.00003848486],"category_scores_gemma":[0.01932762,0.000108847,0.0001302774,0.0006719423,0.0001245083,0.0008602223,0.0002551432,0.002274815,0.00005342779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004182824,"about_ca_system_score_gemma":0.001061257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001252542,"about_ca_topic_score_gemma":0.000404437,"domain_scores_codex":[0.9946856,0.001168892,0.0003641706,0.0004527602,0.0006959706,0.002632527],"domain_scores_gemma":[0.9909261,0.00802999,0.0002387417,0.0002702308,0.0003737152,0.0001612611],"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":[0.0001149406,0.00000663586,0.003165722,0.000002578826,0.00004752844,0.000002104828,0.0004658965,0.0002004004,0.00006050463,0.02844084,0.001581919,0.9659109],"study_design_scores_gemma":[0.0004920831,0.0003692963,0.0004992381,0.00001486926,0.000007236265,0.000239711,0.007057621,0.02248516,0.0000277367,0.8726737,0.09601523,0.0001180983],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8683608,0.01398817,0.0725821,0.04059166,0.00165939,0.0007062029,0.000005602367,0.0001636086,0.001942473],"genre_scores_gemma":[0.8742284,0.03568918,0.004996661,0.0001262683,0.001084917,0.00003950961,0.000006534877,0.00009709446,0.08373147],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9657928,"threshold_uncertainty_score":0.9994645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2458095346805196,"score_gpt":0.4436653148556958,"score_spread":0.1978557801751762,"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."}}