{"id":"W4416909509","doi":"10.65521/ijacect.v14i1.562","title":"API Augmented Reinforcement Learning Framework Utilizing LLMs for Enhanced News-Based Stock Portfolio Strategies","year":2025,"lang":"","type":"article","venue":"International Journal on Advanced Computer Engineering and Communication Technology","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Reinforcement learning; Automatic summarization; Portfolio; Stock market; Stock (firearms); Project portfolio management; Benchmark (surveying); Portfolio optimization","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":[0.0009831777,0.0007188161,0.0008124792,0.0003873159,0.0002437634,0.000953593,0.001072283,0.0006808651,0.002901051],"category_scores_gemma":[0.002358743,0.0002865354,0.0003614553,0.0002756055,0.0003966599,0.0008360305,0.0008867875,0.0009666589,0.0005165728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005257184,"about_ca_system_score_gemma":0.0008779056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003929608,"about_ca_topic_score_gemma":0.003408704,"domain_scores_codex":[0.9996507,0.0001147114,0.0000217901,0.00006484905,0.00009689092,0.00005104858],"domain_scores_gemma":[0.9992748,0.0003455198,0.00009577212,0.00004760483,0.0001896402,0.00004670285],"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":[0.0001374533,0.000140957,0.001088407,0.00006595763,0.00005692418,0.0001336982,0.00008017015,0.8924025,0.003874401,0.009415306,0.001308772,0.09129546],"study_design_scores_gemma":[0.000005345963,0.00001696109,0.00003864487,0.000001473873,0.000003050669,0.000003697296,0.000001798001,0.9986972,0.0002312731,0.0008321623,0.0001660934,0.000002283754],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02667175,0.0002034939,0.9677781,0.0002077579,0.00006306436,0.0000595659,0.00006379807,0.001151407,0.003801045],"genre_scores_gemma":[0.9076186,0.0001187448,0.08791506,0.0001375634,0.00005794991,0.0001763753,0.0001002875,0.00007635045,0.00379895],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003929608,"threshold_uncertainty_score":0.009704947,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02709272405320909,"score_gpt":0.3739594492761544,"score_spread":0.3468667252229453,"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."}}