{"id":"W4414774630","doi":"10.1007/s11135-025-02395-1","title":"Forecasting stock markets in the MENA region: ARIMAX and ensemble machine learning models with SHAP interpretability","year":2025,"lang":"en","type":"article","venue":"Quality & Quantity","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Interpretability; Gradient boosting; Autoregressive integrated moving average; Stock market; Support vector machine; Hyperparameter optimization; Boosting (machine learning); Categorical variable; Hyperparameter; Stock market index","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":[0.002182256,0.0005435614,0.0008192461,0.0005677817,0.000296703,0.001148314,0.0007245899,0.0006326634,0.0006814399],"category_scores_gemma":[0.004828358,0.0003014768,0.0008566949,0.000490753,0.0001816778,0.001522074,0.0004926435,0.001130244,0.0001465732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004581299,"about_ca_system_score_gemma":0.0005379039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02010639,"about_ca_topic_score_gemma":0.01699725,"domain_scores_codex":[0.9997535,0.00009709942,0.00001698089,0.000060881,0.00003760555,0.00003389469],"domain_scores_gemma":[0.9985219,0.000960285,0.0001272765,0.0001030312,0.0002353574,0.00005230624],"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":[0.0003872455,0.0001395588,0.02183346,0.00003592524,0.0002711995,0.00007607281,0.00009132968,0.910193,0.001873017,0.003680662,0.001010849,0.06040776],"study_design_scores_gemma":[0.000002566589,0.000006017642,0.0009619989,0.000001069344,0.000007336405,0.000001616667,0.000004184317,0.9985589,0.00009098894,0.0003347195,0.00002844096,0.000002135195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8801056,0.0006534525,0.1162297,0.0004672972,0.0000839559,0.00001734361,0.0003061637,0.0001853355,0.001951113],"genre_scores_gemma":[0.9829931,0.0001495391,0.01541986,0.00002810481,0.0000670747,0.00001133383,0.0002962186,0.00001795713,0.001016862],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02010639,"threshold_uncertainty_score":0.03997874,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3189768992462003,"score_gpt":0.4374454509363496,"score_spread":0.1184685516901492,"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."}}