{"id":"W2990767007","doi":"10.3233/shti190221","title":"Application of Machine Learning and Grocery Transaction Data to Forecast Effectiveness of Beverage Taxation","year":2019,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Nutritional Studies and Diet","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Lasso (programming language); Benchmark (surveying); Computer science; Transaction data; Decision tree; Machine learning; Regression; Econometrics; Artificial intelligence; Database transaction; Statistics; Economics; Database; Mathematics","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":[0.002481065,0.0005985179,0.0004590271,0.001356089,0.0001454137,0.0005405188,0.0005036764,0.0007525323,0.0008801012],"category_scores_gemma":[0.008675338,0.0001740141,0.0004513947,0.001259014,0.0002220447,0.0006481579,0.0004162032,0.0008693024,0.0002138535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006919463,"about_ca_system_score_gemma":0.0005896408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01617709,"about_ca_topic_score_gemma":0.009346839,"domain_scores_codex":[0.9994379,0.000284325,0.00005132423,0.00009561307,0.00008977649,0.00004097079],"domain_scores_gemma":[0.9950428,0.003648925,0.0004851481,0.0002169931,0.0004834713,0.0001225797],"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":[0.0008711726,0.0006458152,0.1986284,0.0001888812,0.0002678138,0.0002858314,0.00008774843,0.6930962,0.001938827,0.00154522,0.00264634,0.09979771],"study_design_scores_gemma":[0.000007522745,0.00004836441,0.01318848,0.00001130533,0.00001002428,0.00001274491,0.00002124097,0.9854145,0.000426718,0.000569747,0.000282093,0.000007207372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9748095,0.0009944391,0.019667,0.0008485338,0.00007131953,0.00004185898,0.002111913,0.0001598104,0.001295593],"genre_scores_gemma":[0.9852287,0.0002522897,0.01201092,0.00005647244,0.00003719006,0.00002158725,0.001935905,0.00001002919,0.0004469912],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01617709,"threshold_uncertainty_score":0.03216583,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03439041444059976,"score_gpt":0.3538798956242534,"score_spread":0.3194894811836537,"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."}}