{"id":"W7104458993","doi":"10.71781/15656","title":"On the generalization of machine learning models in finance : five essays on bridging the empirical gap","year":2025,"lang":"en","type":"dissertation","venue":"Open MIND","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Mitacs","keywords":"Repartition; Context (archaeology); Decision tree","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007832772,0.0008570738,0.0009776228,0.002137294,0.001098376,0.003786294,0.001349982,0.002460963,0.004351863],"category_scores_gemma":[0.02518733,0.0004038621,0.001173869,0.002577052,0.009941895,0.009889081,0.002592327,0.005518719,0.0006960147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003346258,"about_ca_system_score_gemma":0.001507545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002115063,"about_ca_topic_score_gemma":0.001670933,"domain_scores_codex":[0.9967561,0.001774135,0.0002271055,0.0003976774,0.0006782382,0.0001667677],"domain_scores_gemma":[0.9803419,0.01692425,0.0006249311,0.0009624464,0.0009258089,0.0002207739],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001093624,0.0000224488,0.0003567159,0.0001270152,0.00001715618,0.00004888884,0.0006787757,0.003497508,0.00006027059,0.9658535,0.007545521,0.02178128],"study_design_scores_gemma":[0.000006120982,0.00001337849,0.0004673562,0.0002023835,0.000009190664,0.00004477692,0.000199547,0.005230339,0.00006912279,0.9521106,0.04163415,0.00001288124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03303991,0.1831331,0.3594845,0.2587358,0.005096651,0.00007309171,0.0003268999,0.0002441745,0.1598659],"genre_scores_gemma":[0.7388182,0.1284229,0.05562909,0.02131236,0.01911445,0.0002688908,0.000342068,0.0002844031,0.03580775],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007832772,"threshold_uncertainty_score":0.0414241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3533241481307882,"score_gpt":0.4694936314239501,"score_spread":0.116169483293162,"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."}}