{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001111946,0.0007585518,0.0003205711,0.005485023,0.0003345745,0.001810638,0.0003970363,0.0005281015,0.008670816],"category_scores_gemma":[0.01573622,0.0001796473,0.0004625657,0.003252247,0.0001509771,0.002278316,0.0005567582,0.0005792382,0.008084934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004122216,"about_ca_system_score_gemma":0.0002599494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003799538,"about_ca_topic_score_gemma":0.004142176,"domain_scores_codex":[0.999299,0.000176833,0.00009622782,0.0001273924,0.0002456446,0.00005487489],"domain_scores_gemma":[0.9898839,0.004925174,0.001018594,0.0007449021,0.003169838,0.0002576189],"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":[0.001271149,0.0002201124,0.08694762,0.0003975213,0.0001445665,0.0004236203,0.0007742527,0.00897817,0.02564014,0.001995053,0.04780906,0.8253988],"study_design_scores_gemma":[0.00005997602,0.0006052691,0.415906,0.0003242662,0.0003554937,0.001029219,0.002080731,0.4644871,0.04280021,0.01315477,0.05892638,0.0002705535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.751968,0.002950066,0.1396389,0.001425697,0.0009729934,0.0001916825,0.0475889,0.01398061,0.04128321],"genre_scores_gemma":[0.8971606,0.0007916934,0.05549465,0.00006447827,0.0003669623,0.0001628933,0.03210096,0.0008474924,0.01301029],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008670816,"threshold_uncertainty_score":0.02900672,"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."}}