{"id":"W4297198863","doi":"10.1007/978-3-031-16564-1_37","title":"Similarity Embedded Temporal Transformers: Enhancing Stock Predictions with Historically Similar Trends","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Econometrics; Autoregressive model; Transformer; Computer science; Extrapolation; Heteroscedasticity; Time horizon; Autoregressive integrated moving average; Time series; Stock market; Artificial intelligence; Machine learning; Economics; Finance; Engineering; Mathematics; Statistics; Geography","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":[0.0007590406,0.0004570538,0.0004692207,0.0006800243,0.0001778014,0.000829411,0.000763025,0.0005109491,0.003455855],"category_scores_gemma":[0.003686809,0.0002426591,0.0003756373,0.001082314,0.0002479484,0.002171806,0.001025156,0.0006905277,0.001018395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002562841,"about_ca_system_score_gemma":0.0003859534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001390444,"about_ca_topic_score_gemma":0.002062763,"domain_scores_codex":[0.9997762,0.00003614869,0.00001593425,0.00005894264,0.00009073284,0.00002211252],"domain_scores_gemma":[0.9989711,0.0004937199,0.0001211079,0.0001553372,0.0001975843,0.00006114908],"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":[0.000939159,0.0003574984,0.004258097,0.0001101725,0.00008554749,0.0002080009,0.0001101475,0.1035224,0.03017563,0.01220614,0.004907,0.8431202],"study_design_scores_gemma":[0.00002774802,0.0001207682,0.0009128282,0.000008423342,0.0000417964,0.0001128209,0.00002424566,0.9784495,0.008890541,0.01016149,0.00123923,0.00001055943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1355187,0.0006771029,0.8574491,0.0002272999,0.0002250845,0.00005972028,0.0002885867,0.001834191,0.003720208],"genre_scores_gemma":[0.8415241,0.0006847546,0.1523628,0.0001189323,0.000196697,0.00003161754,0.0005501148,0.0002033043,0.004327706],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003455855,"threshold_uncertainty_score":0.01156098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0696663475278447,"score_gpt":0.3425512067555408,"score_spread":0.2728848592276961,"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."}}