{"id":"W4311435442","doi":"10.36227/techrxiv.21692852","title":"Prediction of the Stock Market Based on Machine Learning and Sentiment Analysis","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"Lakehead University","keywords":"Stock market; Sentiment analysis; Feature engineering; Stock (firearms); Stock market prediction; Computer science; Stock price; Artificial intelligence; Financial economics; Order (exchange); Econometrics; Deep learning; Economics; Machine learning; Finance; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01548454,0.000249914,0.000612696,0.0009887066,0.0003022927,0.0001392663,0.0008837226,0.0001294666,0.01827409],"category_scores_gemma":[0.007563686,0.0001510657,0.0005521183,0.001879074,0.00009797684,0.0000303067,0.002423282,0.0009328793,0.000001768799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001104921,"about_ca_system_score_gemma":0.0001072792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000157772,"about_ca_topic_score_gemma":0.00003469246,"domain_scores_codex":[0.9913429,0.003998886,0.0008698356,0.0009217263,0.002680916,0.0001857613],"domain_scores_gemma":[0.9920129,0.0055398,0.0009492191,0.001244012,0.0001800934,0.00007399896],"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":[0.0001706363,0.00007601833,0.803015,0.00002319405,0.0003647335,0.000001234534,0.0001115444,0.1495186,0.00002651433,0.00002469027,0.003162249,0.04350559],"study_design_scores_gemma":[0.0001562524,0.00006585356,0.2958404,0.00001582371,0.0003676063,7.109417e-7,0.0000698148,0.6974308,0.00005146903,0.0009001522,0.005007462,0.00009368363],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4102389,0.0003959798,0.2640939,0.002262497,0.003951314,0.002529505,0.0009183987,0.0002853675,0.3153241],"genre_scores_gemma":[0.9360726,0.00001078767,0.01881642,0.0001321346,0.00004944632,0.00008073523,0.0000297475,0.00002683042,0.04478129],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5479122,"threshold_uncertainty_score":0.9826233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1061469080793502,"score_gpt":0.3853127485335019,"score_spread":0.2791658404541517,"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."}}