{"id":"W4399178790","doi":"10.2139/ssrn.4848471","title":"Predict Mini Flash Crashes from High-Frequency Data by Machine Learning","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Flash (photography); Computer science; Artificial intelligence; Machine learning; Physics; Optics","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":[0.001109905,0.0009554401,0.0008093717,0.001769879,0.0002465488,0.0007878679,0.0008627845,0.001060069,0.002097446],"category_scores_gemma":[0.004824865,0.0003562405,0.0005994436,0.001267173,0.0002205712,0.001080542,0.0004490454,0.001368157,0.00104305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003903956,"about_ca_system_score_gemma":0.0005399251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005262714,"about_ca_topic_score_gemma":0.005071623,"domain_scores_codex":[0.9997382,0.00006298796,0.0000214403,0.00006952988,0.00005364282,0.0000542383],"domain_scores_gemma":[0.9971285,0.002030485,0.0002513253,0.0001842527,0.0003110918,0.00009438118],"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":[0.0004611556,0.0005329841,0.0737009,0.0001054843,0.0001753591,0.0001300246,0.0000459845,0.7185963,0.002570906,0.001850019,0.004519253,0.1973115],"study_design_scores_gemma":[0.000004490887,0.00001834591,0.002800173,0.000004321365,0.000005817618,0.000007300888,0.000005680095,0.9955023,0.000265471,0.001298633,0.00008418371,0.000003282885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7569749,0.001439347,0.2331526,0.001050493,0.0002160039,0.0001124028,0.002505066,0.001154335,0.00339482],"genre_scores_gemma":[0.9807205,0.0003086496,0.01460489,0.00007028021,0.0001991593,0.00005097672,0.00195857,0.00002830525,0.002058673],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005262714,"threshold_uncertainty_score":0.01046413,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07541331937270833,"score_gpt":0.3755525372299302,"score_spread":0.3001392178572219,"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."}}