{"id":"W4408109759","doi":"10.2139/ssrn.5160381","title":"How do retail investors use order flow data?","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary; University of Toronto","funders":"","keywords":"Order (exchange); Business; Flow (mathematics); Commerce; Industrial organization; Finance; Mathematics; Geometry","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":[0.005011837,0.0003413299,0.0004370812,0.002492755,0.0003351673,0.00820445,0.0007631039,0.001402071,0.005275886],"category_scores_gemma":[0.06188128,0.0004785105,0.0003874722,0.002926334,0.0007413204,0.01420638,0.0008818952,0.001003165,0.002418837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00104627,"about_ca_system_score_gemma":0.000841987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01108217,"about_ca_topic_score_gemma":0.01004573,"domain_scores_codex":[0.997338,0.001065586,0.0002007108,0.0003961977,0.0006911432,0.0003084475],"domain_scores_gemma":[0.9676735,0.02082581,0.005266319,0.002129734,0.00337479,0.0007297965],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004855371,0.0002257077,0.7801173,0.0001702402,0.0003690912,0.0001779484,0.001818273,0.003524297,0.0005320517,0.01774542,0.02169305,0.1731411],"study_design_scores_gemma":[0.0002625856,0.0003173383,0.6233282,0.000722449,0.0008363087,0.0008699312,0.01946516,0.1054593,0.009499734,0.125146,0.1137568,0.0003360485],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8931778,0.003001602,0.01101361,0.01441576,0.0002847889,0.00009549856,0.004007312,0.0005376068,0.07346591],"genre_scores_gemma":[0.9921963,0.0008718624,0.001697158,0.00066537,0.0001175732,0.00001536974,0.001241343,0.0001173092,0.00307774],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01108217,"threshold_uncertainty_score":0.02650547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09830267956233943,"score_gpt":0.2892149985864502,"score_spread":0.1909123190241108,"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."}}