{"id":"W4396620509","doi":"10.1016/j.eswa.2024.124129","title":"Integrating deep transformer and temporal convolutional networks for SMEs revenue and employment growth prediction","year":2024,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada; University of Waterloo","funders":"","keywords":"Computer science; Revenue; Transformer; Artificial intelligence; Convolutional neural network; Machine learning; Finance; Business; Electrical engineering","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":[0.001909142,0.0001533944,0.0002241983,0.0001566477,0.0003606975,0.0003475083,0.0001445751,0.00008270681,0.000007409756],"category_scores_gemma":[0.0002367476,0.0001039707,0.00004367997,0.0004366722,0.0001355905,0.0002171682,0.00001984654,0.0001147171,0.000002756297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005543252,"about_ca_system_score_gemma":0.00006177377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000147066,"about_ca_topic_score_gemma":0.00008661653,"domain_scores_codex":[0.9982596,0.0001307258,0.0004902096,0.0005373613,0.0003893459,0.0001927551],"domain_scores_gemma":[0.9975608,0.001789098,0.0001039576,0.000219763,0.0002135128,0.0001128591],"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":[0.0003269854,0.0001508258,0.06751319,0.0004085866,0.0003990022,0.00000505017,0.01116367,0.0009307803,0.00162853,0.2179015,0.07320664,0.6263653],"study_design_scores_gemma":[0.0007185609,0.0003127332,0.008593544,0.0004920249,0.00006180723,0.0003190229,0.00344033,0.6780472,0.00007237587,0.01274138,0.2947755,0.0004256203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003096696,0.006269522,0.9875672,0.0005680914,0.0002879804,0.001529033,0.0001183941,0.00009508009,0.0004679321],"genre_scores_gemma":[0.9477404,0.00005560045,0.04518303,0.00005232514,0.0005901026,0.005051061,0.0000360285,0.00003111648,0.001260321],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9446437,"threshold_uncertainty_score":0.4239801,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05361556026075728,"score_gpt":0.3618383054063002,"score_spread":0.3082227451455429,"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."}}