{"id":"W4386988846","doi":"10.3905/jfds.2023.1.138","title":"RIFT: Pretraining and Applications for Representations of Interrelated Financial Time Series","year":2023,"lang":"en","type":"article","venue":"The Journal of Financial Data Science","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Pairwise comparison; Portfolio optimization; Computer science; Portfolio; Autoencoder; Artificial intelligence; Representation (politics); Machine learning; Encoder; Artificial neural network; Econometrics; Finance; Economics","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":[0.00137652,0.001127223,0.0006044665,0.0006800393,0.0002667621,0.0007415059,0.001271146,0.001234631,0.005149515],"category_scores_gemma":[0.005133076,0.0005255257,0.000925944,0.0009204714,0.0003513932,0.001839094,0.001233073,0.002808806,0.001620713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005454872,"about_ca_system_score_gemma":0.0007756597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003324932,"about_ca_topic_score_gemma":0.003802552,"domain_scores_codex":[0.9996749,0.0000982017,0.00002507861,0.0000855107,0.00008572912,0.00003070165],"domain_scores_gemma":[0.9990446,0.0005037913,0.00007811502,0.0001687581,0.0001641369,0.00004061952],"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":[0.0001140717,0.0001230151,0.00119388,0.0001258305,0.0001104369,0.0001278582,0.00007317026,0.3675592,0.006919859,0.01321951,0.008581934,0.6018513],"study_design_scores_gemma":[0.000006555518,0.00002876256,0.0001434195,0.000009170876,0.000006711092,0.00002473012,0.000005586255,0.9922162,0.001684505,0.004550935,0.001317639,0.000005683151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01118882,0.0004036952,0.9837545,0.0003177058,0.0001031751,0.00006324486,0.0003021784,0.002321719,0.001545048],"genre_scores_gemma":[0.2292996,0.0007782578,0.7614112,0.0003445394,0.0001493565,0.0003558003,0.001868719,0.0003794756,0.005412997],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005149515,"threshold_uncertainty_score":0.01722682,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1833950529321575,"score_gpt":0.4569542543097912,"score_spread":0.2735592013776337,"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."}}