{"id":"W1483241412","doi":"10.1007/978-3-642-01818-3_7","title":"Financial Forecasting Using Character N-Gram Analysis and Readability Scores of Annual Reports","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":42,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Readability; Computer science; Support vector machine; Artificial intelligence; Benchmark (surveying); n-gram; Natural language processing; Character (mathematics); Portfolio; Task (project management); Machine learning; Finance; Language model; Management; Mathematics","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","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01383212,0.0005281225,0.001463736,0.002785018,0.0002904667,0.0003557417,0.001249651,0.0004150836,0.00005182253],"category_scores_gemma":[0.01679422,0.0004204744,0.000368858,0.002896549,0.001545422,0.000501266,0.0009523102,0.000699919,8.882479e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000188442,"about_ca_system_score_gemma":0.000630365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001188236,"about_ca_topic_score_gemma":0.0003025892,"domain_scores_codex":[0.9924217,0.0002230696,0.001921702,0.00224173,0.002584152,0.0006076091],"domain_scores_gemma":[0.9903537,0.004806113,0.001852631,0.001658632,0.00116576,0.0001631723],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002833493,0.00001773285,0.02327163,0.00001395366,0.00002091437,0.0001044276,0.0004691985,0.008493234,0.00008958049,0.00005970228,0.000003446167,0.9674278],"study_design_scores_gemma":[0.0001446867,0.000310112,0.1070545,0.0005602242,0.0002404024,0.0004664114,0.000001042399,0.403326,0.001268271,0.4854462,0.0002575918,0.0009245762],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1302897,0.0001855236,0.8674137,0.00006478534,0.0008421888,0.0003399134,0.00002386367,0.00003242156,0.0008078626],"genre_scores_gemma":[0.5270359,0.00000473282,0.4722441,0.0001719982,0.0003595305,0.000001770129,0.000002724508,0.00001976001,0.0001595167],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9665033,"threshold_uncertainty_score":0.9998247,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08693918484533111,"score_gpt":0.3612053647158101,"score_spread":0.274266179870479,"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."}}