{"id":"W4297492116","doi":"10.1007/s00291-022-00693-w","title":"Machine learning techniques for cross-sectional equity returns’ prediction","year":2022,"lang":"en","type":"article","venue":"OR Spectrum","topic":"Financial Markets and Investment Strategies","field":"Economics, Econometrics and Finance","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Universität Bremen","keywords":"Machine learning; Computer science; Artificial intelligence; Random forest; Support vector machine; Portfolio; Benchmark (surveying); Artificial neural network; Stock (firearms); Econometrics; Decision tree; Regression; Economics; Financial economics; Mathematics; Statistics","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":[0.005560388,0.0006818144,0.0009210311,0.003137315,0.0002990419,0.0009175958,0.0008399428,0.0009495979,0.002006091],"category_scores_gemma":[0.01563138,0.0002984179,0.0007111866,0.002081598,0.0003388529,0.001275812,0.0008201567,0.001380402,0.0009325044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005412893,"about_ca_system_score_gemma":0.0006523038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004883688,"about_ca_topic_score_gemma":0.002861426,"domain_scores_codex":[0.9987158,0.0006552098,0.0001102618,0.0001922264,0.0002385079,0.00008811381],"domain_scores_gemma":[0.9910499,0.007170112,0.0006142395,0.0004587465,0.0006057539,0.0001012624],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002078821,0.0002317162,0.03356589,0.0001132373,0.0003447344,0.0001126455,0.0000611086,0.7479348,0.001171521,0.004311097,0.002057363,0.2098881],"study_design_scores_gemma":[0.000003434447,0.00001936775,0.001948393,0.0000075049,0.000007261031,0.00001369182,0.000005613036,0.9959314,0.000176313,0.001740174,0.0001427497,0.000004008022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3743217,0.00584179,0.6105172,0.001570988,0.0002173436,0.00008292135,0.000889347,0.002623636,0.003935124],"genre_scores_gemma":[0.939846,0.0007798401,0.05702301,0.00009602251,0.0001369414,0.0000664478,0.0007512979,0.00004831936,0.001252138],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005560388,"threshold_uncertainty_score":0.02940649,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05480379686306359,"score_gpt":0.2802640547166015,"score_spread":0.2254602578535379,"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."}}