{"id":"W4392203267","doi":"10.1016/j.ijforecast.2024.02.001","title":"The short-term predictability of returns in order book markets: A deep learning perspective","year":2024,"lang":"en","type":"article","venue":"International Journal of Forecasting","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Engineering and Physical Sciences Research Council","keywords":"Predictability; Computer science; Representation (politics); Inference; Perspective (graphical); Term (time); Order (exchange); Machine learning; Artificial intelligence; Order book; High-frequency trading; Statistical inference; Econometrics; Data science; Algorithmic trading; Economics; Financial economics; Mathematics; Finance; Statistics","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"],"consensus_categories":[],"category_scores_codex":[0.01746366,0.000161961,0.0003371848,0.0006950144,0.0001100505,0.0004117246,0.001332027,0.00007830642,0.0002674307],"category_scores_gemma":[0.08059182,0.0001010894,0.0002656082,0.001001134,0.0002236967,0.0006649021,0.0002705587,0.0008614919,0.000003483988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000434222,"about_ca_system_score_gemma":0.0003116171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001886733,"about_ca_topic_score_gemma":0.00007702492,"domain_scores_codex":[0.9945264,0.00084804,0.001727051,0.0003251286,0.002308322,0.0002650405],"domain_scores_gemma":[0.9811679,0.01402988,0.0007172233,0.0002122697,0.003787312,0.00008542238],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008720153,0.00007220588,0.1531114,0.00001610618,0.0002916548,0.0004080141,0.007556142,0.002707937,0.0004829387,0.001452784,0.0006802624,0.8323485],"study_design_scores_gemma":[0.00119103,0.0006299264,0.2484769,0.002292616,0.0000944612,0.004350112,0.01583398,0.6328841,0.0008685684,0.07718676,0.01571167,0.0004798365],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.922327,0.006101473,0.04285293,0.002180891,0.004996579,0.0002392814,0.0000112729,0.00003350707,0.02125703],"genre_scores_gemma":[0.9929072,0.0000816479,0.005952689,0.00002090616,0.0004799451,0.000004130194,4.856261e-7,0.0000184267,0.0005345716],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8318686,"threshold_uncertainty_score":0.9271528,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07891228350161848,"score_gpt":0.4145048008010231,"score_spread":0.3355925172994046,"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."}}