{"id":"W3109672140","doi":"","title":"Predicting S&P500 Index direction with Transfer Learning and a Causal Graph as main Input.","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Financial market; Computer science; Index (typography); Portfolio; Econometrics; Benchmark (surveying); Graph; Representation (politics); Artificial intelligence; Sample (material); Machine learning; Finance; Economics; Geography; Theoretical computer science","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002847056,0.0004551216,0.0006474796,0.0007562526,0.0004318527,0.0003060143,0.0007489331,0.0004149374,0.0001682195],"category_scores_gemma":[0.002621664,0.00042367,0.0002026874,0.001932091,0.0003088633,0.0003137732,0.0008494578,0.00167788,0.00002638279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001434168,"about_ca_system_score_gemma":0.0002686348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005099315,"about_ca_topic_score_gemma":0.0003185713,"domain_scores_codex":[0.9953141,0.001379042,0.0004389056,0.001909883,0.0005240252,0.0004339986],"domain_scores_gemma":[0.9963711,0.002115985,0.0003179597,0.0005647829,0.0002729785,0.0003571837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00131543,0.00005700451,0.8357419,0.00008313935,0.0002812718,0.0008013129,0.001967074,0.1421039,0.0002125653,0.003208122,0.0001297211,0.01409852],"study_design_scores_gemma":[0.003296397,0.001159973,0.2076816,0.0006939194,0.0006830587,0.0002505539,0.005003078,0.5961674,0.0003311195,0.1790625,0.003582025,0.002088258],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7203227,0.00002841025,0.2702389,0.00009634672,0.0003141338,0.0003240069,0.00001168814,0.0002238726,0.008440011],"genre_scores_gemma":[0.9959772,0.0000563831,0.001119555,0.00005406138,0.0001252827,0.00000224404,0.000006631442,0.00004759191,0.002611011],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6280603,"threshold_uncertainty_score":0.9998215,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1242862070205974,"score_gpt":0.2712127639130122,"score_spread":0.1469265568924148,"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."}}