{"id":"W2750444890","doi":"10.1016/j.ijleo.2017.12.038","title":"Applying deep bidirectional LSTM and mixture density network for basketball trajectory prediction","year":2017,"lang":"en","type":"article","venue":"Optik","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":75,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Trajectory; Basketball; Artificial intelligence; Hidden Markov model; Machine learning; Convergence (economics); Pointer (user interface); Data mining","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":[0.0003406651,0.00009058104,0.0001818453,0.00004403235,0.0005985332,0.0001347119,0.0001013568,0.00008683703,0.0001019621],"category_scores_gemma":[0.00002911502,0.0001015086,0.00006571293,0.00002761947,0.00004272529,0.0001817003,0.00002935124,0.00008489903,0.00001623783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002980347,"about_ca_system_score_gemma":0.000008484046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001041612,"about_ca_topic_score_gemma":0.0001270937,"domain_scores_codex":[0.9993396,0.000001625016,0.0002045219,0.0002508686,0.00002280119,0.0001805534],"domain_scores_gemma":[0.9994462,0.00001870032,0.0002161673,0.0002369098,0.00002628178,0.0000557854],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004310236,0.00003418089,0.9422362,0.00004623387,0.00007800731,0.000001644369,0.0000969401,0.002455466,0.00001251384,0.04094315,0.006755503,0.007297057],"study_design_scores_gemma":[0.0003970069,0.0000414988,0.592694,0.0000142832,0.0000125932,0.000006033001,0.00001115988,0.125786,0.00001588952,0.006670851,0.2741715,0.0001791229],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9051282,0.004509452,0.04400668,0.0005924949,0.003860565,0.000986032,0.000347148,0.00008752443,0.04048192],"genre_scores_gemma":[0.9938961,0.0005077648,0.00272186,0.0001358225,0.0008621863,0.00007447939,0.00002883957,0.00001560803,0.001757375],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3495421,"threshold_uncertainty_score":0.4603494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02652370961729971,"score_gpt":0.2171201489304239,"score_spread":0.1905964393131242,"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."}}