{"id":"W3017186808","doi":"10.1007/s11408-020-00350-8","title":"Portfolio creation using artificial neural networks and classification probabilities: a Canadian study","year":2020,"lang":"en","type":"article","venue":"Financial markets and portfolio management","topic":"Financial Markets and Investment Strategies","field":"Economics, Econometrics and Finance","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Portfolio; Econometrics; Artificial neural network; Ranking (information retrieval); Economics; Excess return; Yield (engineering); Stock exchange; Financial economics; Sample (material); Actuarial science; Stock market index; Stock (firearms); Statistics; Stock market; Artificial intelligence; Computer science; Mathematics; Finance; Engineering; Geography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.004011884,0.00058292,0.0004581541,0.002462164,0.001887577,0.002344626,0.001681127,0.0006344495,0.002677933],"category_scores_gemma":[0.02095096,0.0003563431,0.0006687307,0.006755536,0.001091746,0.001893943,0.0005162315,0.001131687,0.000271263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02718742,"about_ca_system_score_gemma":0.01562323,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9656596,"about_ca_topic_score_gemma":0.9451299,"domain_scores_codex":[0.9987463,0.0003725895,0.00006067808,0.0001500667,0.0005448324,0.0001255607],"domain_scores_gemma":[0.9900294,0.005728642,0.0006180988,0.0005124331,0.002852875,0.0002586045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001239633,0.001336433,0.2642908,0.0003499307,0.0006028459,0.0006092957,0.002295706,0.1021956,0.001225224,0.06596123,0.01609175,0.5438015],"study_design_scores_gemma":[0.0004226391,0.0004601443,0.340843,0.0002382809,0.0005228157,0.0005942119,0.002861235,0.5953842,0.003836072,0.02056154,0.03407913,0.0001968144],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9415949,0.005483716,0.01481991,0.001649691,0.00004095493,0.0001704913,0.0009748843,0.00009424293,0.0351711],"genre_scores_gemma":[0.9759483,0.003654025,0.01003484,0.00008502261,0.00002111775,0.00002658675,0.0007665145,0.00003638459,0.009427157],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03434038,"threshold_uncertainty_score":0.1972595,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04891631825280772,"score_gpt":0.2277285992022465,"score_spread":0.1788122809494388,"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."}}