{"id":"W3164753059","doi":"10.2139/ssrn.3305277","title":"Investigating Limit Order Book Features for Short-Term Price Prediction: A Machine Learning Approach","year":2018,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Order book; Term (time); Limit (mathematics); Order (exchange); Computer science; High-frequency trading; Artificial intelligence; Financial market; Machine learning; Econometrics; Algorithmic trading; Financial economics; Economics; Mathematics; 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":["metaresearch","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.02246486,0.0003064678,0.0004164579,0.0004114425,0.001398909,0.000497071,0.001065175,0.0001820886,0.0001233381],"category_scores_gemma":[0.01764593,0.0002294268,0.0002314821,0.001102835,0.0002489337,0.0005579483,0.0001823821,0.002888984,0.00001987445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005369462,"about_ca_system_score_gemma":0.001612473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001212056,"about_ca_topic_score_gemma":0.00007629499,"domain_scores_codex":[0.9937769,0.0008218003,0.0008780785,0.0006867767,0.001367262,0.002469186],"domain_scores_gemma":[0.9960148,0.001780841,0.0005421559,0.0004220513,0.0009958562,0.00024429],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005718213,0.000219385,0.09641837,0.00003431839,0.0006311871,0.000004248237,0.003559551,0.002033189,0.003227714,0.02960517,0.01361979,0.8500752],"study_design_scores_gemma":[0.003869754,0.005534506,0.02682198,0.000200763,0.000329358,0.009288416,0.004892509,0.2000525,0.001052868,0.6033218,0.143044,0.001591563],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09896816,0.005190837,0.8728424,0.0009086682,0.001052898,0.0006876243,0.00000926268,0.0001978667,0.02014225],"genre_scores_gemma":[0.7840964,0.0004675012,0.1603357,0.0006228804,0.005736277,0.0001039997,0.00001968275,0.000157675,0.04845988],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8484837,"threshold_uncertainty_score":0.9999011,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06759535854628615,"score_gpt":0.3614725632963628,"score_spread":0.2938772047500767,"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."}}