{"id":"W4386752858","doi":"10.21203/rs.3.rs-3344960/v1","title":"AEformer: Asymmetric Embedding Transformer for Stock Market Prediction based on Investor Sentiment","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China","keywords":"Stock market; Stock (firearms); Econometrics; Embedding; Volatility (finance); Transformer; Financial economics; Computer science; Economics; Artificial intelligence; Engineering","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":[0.0008943029,0.0007355249,0.0005609251,0.0005871021,0.0001599241,0.0005855112,0.0007292152,0.000576968,0.002369936],"category_scores_gemma":[0.002719423,0.0002964199,0.0004591418,0.0004913482,0.0002892281,0.001404881,0.0006500494,0.000980286,0.0007252597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003293485,"about_ca_system_score_gemma":0.0004764257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00275058,"about_ca_topic_score_gemma":0.003153204,"domain_scores_codex":[0.9997576,0.00006786796,0.0000192638,0.00005763671,0.00006418009,0.00003341765],"domain_scores_gemma":[0.9992021,0.0003699386,0.00008120348,0.0000913078,0.0002078317,0.00004765141],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005794499,0.0003621791,0.00625009,0.0001301239,0.0001430792,0.0002029225,0.0001205059,0.3661804,0.03242895,0.01011027,0.006080638,0.5774114],"study_design_scores_gemma":[0.000003924799,0.00002078273,0.0002344734,0.000002176303,0.000005906989,0.00001280052,0.000003435433,0.9966555,0.001793941,0.001118772,0.0001452037,0.000003195419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08869895,0.0004193968,0.907077,0.0003815263,0.0001229763,0.00005700961,0.0002361489,0.001256823,0.001750182],"genre_scores_gemma":[0.899603,0.0003507489,0.09572975,0.0001707114,0.00009323288,0.00005841425,0.0004463551,0.00007108359,0.003476714],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00275058,"threshold_uncertainty_score":0.007928252,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3470055093165934,"score_gpt":0.5260834944048893,"score_spread":0.1790779850882959,"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."}}