{"id":"W4403437453","doi":"10.1007/978-3-031-72393-3_5","title":"SARF: Stock Market Prediction with Sentiment-Augmented Random Forest","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"British Columbia Institute of Technology","funders":"","keywords":"Random forest; Stock market prediction; Stock market; Econometrics; Financial economics; Geography; Economics; Computer science; Artificial intelligence; Archaeology","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":[],"consensus_categories":[],"category_scores_codex":[0.002195606,0.0003396892,0.0005150138,0.0004585359,0.0008576766,0.0005179129,0.001700744,0.0002112813,0.00001013707],"category_scores_gemma":[0.0004184329,0.0002184743,0.0002680115,0.0004887125,0.0005953524,0.0003468653,0.0007794168,0.0004913895,0.000001628806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008915339,"about_ca_system_score_gemma":0.0001755992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000174584,"about_ca_topic_score_gemma":0.0001109804,"domain_scores_codex":[0.9976184,0.00003342529,0.001020188,0.0002584201,0.0008165358,0.0002530534],"domain_scores_gemma":[0.99635,0.001840413,0.0006711984,0.0007510134,0.0003245929,0.00006272861],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003536776,0.00001559658,0.00005799411,0.0002091845,0.0002604158,2.506495e-7,0.001136404,0.9366736,0.000004559156,0.01296188,0.001556754,0.04708793],"study_design_scores_gemma":[0.0004915129,0.0001188258,0.0001934879,0.0004168153,0.0001517845,0.00002872209,0.000009663754,0.9182079,0.00001880105,0.006250588,0.07383578,0.0002761595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004027649,0.0003753396,0.9788408,0.0007050672,0.001096195,0.0009660223,0.0002060449,0.00008522577,0.0173225],"genre_scores_gemma":[0.008627731,0.00004847896,0.9886903,0.00009491287,0.0002376981,0.00005118965,0.00004506708,0.00003664909,0.002167997],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07227902,"threshold_uncertainty_score":0.8909125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04885663924204735,"score_gpt":0.3047854248384408,"score_spread":0.2559287855963934,"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."}}