{"id":"W2753913847","doi":"10.15353/vsnl.v3i1.166","title":"Opening the Black Box of Financial AI with CLEAR-Trade: A CLass-Enhanced Attentive Response Approach for Explaining and Visualizing Deep Learning-Driven Stock Market Prediction","year":2017,"lang":"en","type":"preprint","venue":"Journal of Computational Vision and Imaging Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Vector Institute; Canadian Institute for Advanced Research; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Interpretability; Deep learning; Artificial intelligence; Machine learning; Computer science; Financial market; Stock market; Stock (firearms); Finance; Economics; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.0007138902,0.0009352151,0.0003417745,0.0006832256,0.0003491822,0.001847034,0.001111889,0.001408455,0.008115354],"category_scores_gemma":[0.003179083,0.0003521031,0.0008351066,0.0003090043,0.0009281862,0.002276456,0.002287379,0.002487231,0.0006253521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005297943,"about_ca_system_score_gemma":0.0005389577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001957771,"about_ca_topic_score_gemma":0.002361083,"domain_scores_codex":[0.999821,0.00006937978,0.00000820303,0.00004201484,0.00003563142,0.00002371139],"domain_scores_gemma":[0.9990582,0.0005135295,0.000105916,0.0001486664,0.00009757268,0.00007616773],"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":[0.0009891702,0.0003360734,0.005189484,0.0006584115,0.000188076,0.0007480843,0.002233937,0.3822715,0.06973509,0.1644543,0.0322709,0.3409249],"study_design_scores_gemma":[0.00003412369,0.00006767693,0.0008718744,0.00004678679,0.0000221558,0.00009523518,0.00009846558,0.9132845,0.0122691,0.06555212,0.007624354,0.00003359987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04330811,0.0005708994,0.9405242,0.002153245,0.00018998,0.00007049643,0.0005005416,0.006753402,0.005929093],"genre_scores_gemma":[0.6207637,0.0006399234,0.371559,0.000640302,0.0001238532,0.0001488538,0.0005645267,0.0008511277,0.004708768],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008115354,"threshold_uncertainty_score":0.02714854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02321433490793953,"score_gpt":0.3150460745439577,"score_spread":0.2918317396360182,"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."}}