{"id":"W3106063491","doi":"10.1016/j.compeleceng.2020.106905","title":"Predicting market movement direction for bitcoin: A comparison of time series modeling methods","year":2020,"lang":"en","type":"article","venue":"Computers & Electrical Engineering","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":87,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University; Toronto Metropolitan University; Wilfrid Laurier University","funders":"","keywords":"Autoregressive integrated moving average; Artificial neural network; Random forest; Autoregressive model; Trading strategy; Artificial intelligence; Computer science; Series (stratigraphy); Time series; Momentum (technical analysis); Perceptron; Feature engineering; Econometrics; Machine learning; Movement (music); Feature (linguistics); Moving average; Multilayer perceptron; Deep learning; Economics; Finance","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":[],"consensus_categories":[],"category_scores_codex":[0.0002705428,0.0001457261,0.0003236316,0.0001188531,0.00008426569,0.00003502801,0.0005060151,0.00009891979,0.000001465399],"category_scores_gemma":[0.0001208291,0.0001576608,0.0000896726,0.0007363965,0.00001306956,0.0001341114,0.0001847276,0.0002109316,8.754391e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004966548,"about_ca_system_score_gemma":0.00002273132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005363825,"about_ca_topic_score_gemma":1.991051e-7,"domain_scores_codex":[0.9988601,0.00002860702,0.0003644,0.0003577768,0.0001197201,0.0002694585],"domain_scores_gemma":[0.9992809,0.0002288554,0.00008701807,0.0002434726,0.0000725346,0.00008727133],"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":[0.0000391352,0.0001676406,0.0003194606,0.0001813879,0.0001487562,0.00000134084,0.001037991,0.6893888,0.0406644,0.04771002,0.001257781,0.2190833],"study_design_scores_gemma":[0.0001721354,0.0001962005,0.00003171703,0.00001481565,0.00001013524,0.000002127945,0.000003914801,0.982675,0.01528749,0.0007414766,0.0007254925,0.0001395525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005564534,0.0003329517,0.9919776,0.001055605,0.00009928158,0.0002912078,0.000001377579,0.0006363894,0.00004108954],"genre_scores_gemma":[0.3129656,0.000008342936,0.6867955,0.00009596455,0.0000591737,0.00005676008,0.000001766429,0.00001204119,0.000004860695],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.307401,"threshold_uncertainty_score":0.6429222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01467037997603278,"score_gpt":0.262775059200566,"score_spread":0.2481046792245333,"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."}}