{"id":"W7117748732","doi":"10.18280/isi.301122","title":"Hybrid CNN–LSTM Integrated with Temporal Fusion Transformer for Accurate and Interpretable Stock Market Forecasting","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Stock market; Fusion; Sensor fusion; Transformer; Time series; Probabilistic forecasting","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01073622,0.0009993447,0.001366316,0.001991896,0.001763123,0.002980254,0.001037139,0.0004140062,0.0004802274],"category_scores_gemma":[0.01237235,0.0007842023,0.0003256839,0.002672127,0.0008525237,0.009058782,0.0002929603,0.0006757093,0.00002066982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007227287,"about_ca_system_score_gemma":0.001202352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002508861,"about_ca_topic_score_gemma":0.000094581,"domain_scores_codex":[0.9921903,0.0007921693,0.003574369,0.0009254931,0.001205377,0.001312266],"domain_scores_gemma":[0.9897264,0.004678887,0.001871279,0.0008535599,0.002530859,0.0003390628],"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":[0.005051648,0.00005574839,0.004769297,0.001526363,0.0002435274,0.000005275555,0.006513465,0.0004319248,0.0001020954,0.0003563951,0.006959913,0.9739844],"study_design_scores_gemma":[0.00436112,0.001545109,0.004353627,0.005354976,0.000403164,0.0003001687,0.009577986,0.9003077,0.002104836,0.01813297,0.05223246,0.001325838],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2306551,0.000427683,0.7232807,0.0001873857,0.001487307,0.003192197,0.0003288727,0.0001773108,0.04026346],"genre_scores_gemma":[0.9290518,0.00006271277,0.06602118,0.000367326,0.00008062289,0.0004766132,0.0001622405,0.00005668715,0.00372087],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9726585,"threshold_uncertainty_score":0.9995365,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04589230206902946,"score_gpt":0.317053447230112,"score_spread":0.2711611451610826,"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."}}