{"id":"W2913024470","doi":"10.48550/arxiv.1901.10534","title":"Investigating Limit Order Book Characteristics for Short Term Price Prediction: a Machine Learning Approach","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Limit (mathematics); Term (time); Order book; Order (exchange); Computer science; Artificial intelligence; Financial market; High-frequency trading; Machine learning; Dynamics (music); Econometrics; Baseline (sea); Algorithmic trading; Financial economics; Economics; Mathematics; Finance; Psychology; Physics","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","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005932059,0.0005931302,0.0008820874,0.0006644792,0.0007337197,0.0004160128,0.002102094,0.0006201383,0.0002588995],"category_scores_gemma":[0.01436255,0.0005951035,0.0003931176,0.00136368,0.0004775281,0.0004073632,0.002363963,0.001345793,0.00005243548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000290698,"about_ca_system_score_gemma":0.0003788114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002099022,"about_ca_topic_score_gemma":0.000005198055,"domain_scores_codex":[0.9946913,0.0009343257,0.0009124745,0.002267052,0.0005409645,0.0006538981],"domain_scores_gemma":[0.9928206,0.002797549,0.001041837,0.001515617,0.001439616,0.0003848068],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006347382,0.0004646843,0.8370674,0.0007131566,0.0007645008,0.0001013673,0.002515887,0.1066665,0.000280485,0.004844055,0.01139097,0.03455617],"study_design_scores_gemma":[0.0004964185,0.0001811504,0.02679393,0.0001828052,0.0002477256,0.00002242266,0.0001594008,0.9435419,0.00003881096,0.01092357,0.01671059,0.0007012832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2820076,0.00006789253,0.6997248,0.00004623142,0.001274873,0.001069464,0.0001759239,0.0003352743,0.01529799],"genre_scores_gemma":[0.8946537,0.0000674495,0.07898885,0.0001896374,0.001092293,0.00002124563,0.0002518276,0.0001163689,0.02461863],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8368754,"threshold_uncertainty_score":0.9996501,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2494304213569411,"score_gpt":0.2926912242073922,"score_spread":0.04326080285045111,"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."}}