{"id":"W3021018660","doi":"10.3390/jrfm13050093","title":"Finding Nemo: Predicting Movie Performances by Machine Learning Methods","year":2020,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Cinema and Media Studies","field":"Economics, Econometrics and Finance","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Machine learning; Computer science; Sample (material); Quantile regression; Film industry; Feature selection; Bayesian probability; Regression analysis; Variable (mathematics); Movie theater; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0008627051,0.0001173889,0.0003997294,0.000133004,0.000215745,0.00004261112,0.0001137869,0.00003719261,0.00003541209],"category_scores_gemma":[0.000410586,0.000110101,0.00009590057,0.0001858287,0.00002905956,0.0001726944,0.0001056547,0.000317446,0.000009852849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000224071,"about_ca_system_score_gemma":0.000005102298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002403128,"about_ca_topic_score_gemma":0.000003165591,"domain_scores_codex":[0.9990104,0.00002390383,0.0005704121,0.0001611121,0.00005110826,0.000183089],"domain_scores_gemma":[0.999165,0.00005745352,0.0006109768,0.0000486634,0.00002126755,0.00009665205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001095426,0.00004852831,0.5233018,0.0001919158,0.0001074836,0.00002935219,0.005280601,0.0002761512,0.00002104042,0.005723064,0.005052791,0.4598577],"study_design_scores_gemma":[0.001283317,0.0004010924,0.05089718,0.0000589001,0.00007092837,0.000007229116,0.001028844,0.005134614,0.00004802498,0.002116128,0.9387373,0.0002164069],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6092737,0.08337496,0.2910001,0.002391392,0.001664182,0.0003025146,0.00007458869,0.00004216344,0.01187637],"genre_scores_gemma":[0.9430144,0.04224563,0.01363825,0.0003185152,0.0004872114,0.000003782986,0.000002287342,0.00001432418,0.0002755553],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9336845,"threshold_uncertainty_score":0.448979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02348991293964413,"score_gpt":0.2473087846104894,"score_spread":0.2238188716708452,"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."}}