{"id":"W3198420687","doi":"10.2139/ssrn.3907281","title":"Macroeconomic Predictions using Payments Data and Machine Learning","year":2021,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Bank of Canada; Government of Canada","funders":"","keywords":"Payment; Computer science; Economics; Machine learning; Econometrics; Artificial intelligence; Finance","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":[0.01495757,0.0001379536,0.0002499618,0.0002026722,0.000653401,0.0004036803,0.0007748455,0.00005811852,0.0002666217],"category_scores_gemma":[0.006016606,0.0001163538,0.00006260999,0.0004102165,0.00006349305,0.0005284045,0.0006573047,0.001743568,0.00002114352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004062952,"about_ca_system_score_gemma":0.001925213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004694685,"about_ca_topic_score_gemma":0.0005674324,"domain_scores_codex":[0.9962361,0.0008433969,0.0005734065,0.0005287951,0.0005166365,0.001301705],"domain_scores_gemma":[0.9978505,0.0009268039,0.0003440499,0.0005902495,0.0001597931,0.0001285584],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007129317,0.00006172993,0.2935804,0.000003150616,0.0002953151,0.0000328898,0.0002122933,0.001837397,0.001418145,0.004020269,0.0003497457,0.6981174],"study_design_scores_gemma":[0.001652529,0.0002313735,0.0142541,0.00004683981,0.0001618094,0.01594729,0.004040798,0.4349487,0.0001895518,0.4856887,0.04238534,0.0004529504],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6802194,0.005434381,0.3114417,0.000639539,0.0006693098,0.00007582358,0.0000278639,0.00003406117,0.001457944],"genre_scores_gemma":[0.97953,0.001779683,0.01220105,0.00007513131,0.0003567704,0.000001078047,0.00001447729,0.00002986289,0.006011974],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6976644,"threshold_uncertainty_score":0.7575032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1363937148231179,"score_gpt":0.4008348133103739,"score_spread":0.2644410984872561,"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."}}