{"id":"W2307101150","doi":"10.1016/j.knosys.2016.03.014","title":"Modelling high-frequency FX rate dynamics: A zero-delay multi-dimensional HMM-based approach","year":2016,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University; TD Bank Group","funders":"","keywords":"Hidden Markov model; Computer science; Markov chain; Random walk; Hidden semi-Markov model; Zero (linguistics); Econometrics; Algorithm; Markov model; Mathematics; Speech recognition; Variable-order Markov model; Statistics; Machine learning","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002074135,0.000525653,0.001023551,0.0005769962,0.0003531156,0.0001300331,0.0005111853,0.0004197731,0.0000553232],"category_scores_gemma":[0.0001899912,0.0004695188,0.0003559128,0.0004797998,0.0001405545,0.0003097145,0.00005938384,0.0003008989,0.001218143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007834451,"about_ca_system_score_gemma":0.0002921393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001865366,"about_ca_topic_score_gemma":0.0001043098,"domain_scores_codex":[0.9960871,0.0001637315,0.001589931,0.001219826,0.000117279,0.0008220903],"domain_scores_gemma":[0.9975179,0.0003411353,0.0006125796,0.0009652633,0.0002980534,0.0002650247],"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":[0.0001464325,0.0009381278,0.01545054,0.0005162068,0.00009704685,0.00001227021,0.0002725988,0.7823569,0.0002661589,0.1990265,0.0003352321,0.000582089],"study_design_scores_gemma":[0.00277306,0.00007744004,0.0001682985,0.0003038012,0.00001659185,0.000001980724,0.00001488292,0.9893418,0.00005612091,0.005043209,0.001523176,0.0006796477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.157942,0.003459317,0.8330309,0.000112759,0.001490995,0.0006526509,0.0005586604,0.000199153,0.002553521],"genre_scores_gemma":[0.9840174,0.00001359988,0.01363595,0.0000745514,0.0002826601,0.0002147486,0.0001278651,0.0001146013,0.001518612],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8260754,"threshold_uncertainty_score":0.9997756,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05234806979324771,"score_gpt":0.2290961020454641,"score_spread":0.1767480322522164,"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."}}