{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008633458,0.0005492629,0.0004101619,0.0009378041,0.0001683059,0.0008020706,0.0002954088,0.0004522939,0.001290694],"category_scores_gemma":[0.00259704,0.0001866261,0.0005083062,0.0005652151,0.0001448761,0.0007703416,0.0002087119,0.0006030825,0.0005232655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000459839,"about_ca_system_score_gemma":0.0003081018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004692251,"about_ca_topic_score_gemma":0.004099096,"domain_scores_codex":[0.9997632,0.00005817856,0.0000194406,0.00004757802,0.00007282724,0.0000387961],"domain_scores_gemma":[0.9991898,0.0003898401,0.0001033638,0.00005693357,0.0002200502,0.00004000856],"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":[0.0005220525,0.0006034331,0.07138426,0.0001247683,0.0003012701,0.0002914919,0.0001272337,0.3577783,0.02137628,0.004956893,0.01646701,0.5260671],"study_design_scores_gemma":[0.000002822582,0.00001585564,0.002969582,0.000002987716,0.000003995433,0.00000627021,0.000007409083,0.9952899,0.001084882,0.0004306961,0.0001823091,0.000003177291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8204418,0.0008411295,0.1654985,0.001132912,0.0003757662,0.0001086461,0.001153101,0.0009385822,0.009509632],"genre_scores_gemma":[0.9557659,0.0002596609,0.04002884,0.00006243544,0.0001198276,0.00002808647,0.001125236,0.00002550993,0.002584531],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004692251,"threshold_uncertainty_score":0.009329915,"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."}}