{"id":"W4286977784","doi":"10.48550/arxiv.2109.07005","title":"WaveCorr: Correlation-savvy Deep Reinforcement Learning for Portfolio\\n Management","year":2021,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Portfolio; Exploit; Computer science; Asset management; Project portfolio management; Sharpe ratio; Artificial intelligence; Invariant (physics); Asset allocation; Portfolio optimization; Asset (computer security); Econometrics; Economics; Mathematics; Financial economics; Finance","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.008519677,0.001298905,0.00167988,0.001793154,0.001691993,0.000972315,0.003021923,0.0009690907,0.0065815],"category_scores_gemma":[0.004372868,0.001546348,0.001776372,0.003587831,0.0004405282,0.0009345317,0.005192447,0.001763352,0.0003694909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001260444,"about_ca_system_score_gemma":0.0005748927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001078609,"about_ca_topic_score_gemma":0.00005729314,"domain_scores_codex":[0.9888147,0.001669709,0.002181147,0.004616972,0.001099357,0.001618153],"domain_scores_gemma":[0.9856976,0.005548088,0.002863963,0.003148597,0.001977282,0.0007644281],"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":[0.0006160202,0.0001568035,0.009915775,0.000232822,0.0006764989,0.0005860585,0.0006685929,0.9057634,0.00000532218,0.02429057,0.0007321294,0.05635595],"study_design_scores_gemma":[0.002291713,0.0003026589,0.005649848,0.0005177511,0.001053448,0.00002675072,0.0070758,0.9464021,0.00004086098,0.01969094,0.01541692,0.001531254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0572689,0.0001706328,0.8627312,0.000059357,0.005199126,0.002471666,0.000007474771,0.0001892989,0.07190239],"genre_scores_gemma":[0.85855,0.0009401104,0.018445,0.0001310195,0.0002500191,0.00002234847,0.0001702572,0.0001132499,0.1213781],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8442861,"threshold_uncertainty_score":0.9999763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1393615856705379,"score_gpt":0.2725513304994812,"score_spread":0.1331897448289433,"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."}}