{"id":"W2965426125","doi":"10.1007/978-3-030-24409-5_16","title":"Guiding Public Health Policy by Using Grocery Transaction Data to Predict Demand for Unhealthy Beverages","year":2019,"lang":"en","type":"book-chapter","venue":"Studies in computational intelligence","topic":"Nutritional Studies and Diet","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Lasso (programming language); Benchmark (surveying); Transaction data; Mean squared error; Econometrics; Decision tree; Regression; Computer science; Discounting; Competition (biology); Machine learning; Database transaction; Business; Economics; Statistics; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000760496,0.0003806459,0.0008820678,0.0004328555,0.0003485955,0.00002829447,0.0002714395,0.0001439477,0.00002218969],"category_scores_gemma":[0.0003861505,0.0003792244,0.000118586,0.0001760876,0.0001742334,0.0001481909,0.0002465003,0.0002350614,0.0000170024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001147412,"about_ca_system_score_gemma":0.001016593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001502531,"about_ca_topic_score_gemma":0.00007192203,"domain_scores_codex":[0.9971902,0.00002994281,0.000911879,0.0008135751,0.0005810761,0.0004733542],"domain_scores_gemma":[0.9976196,0.0009382084,0.0002930561,0.0003195994,0.0006309426,0.0001986422],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0018046,0.0009349179,0.0007589826,0.01834482,0.004829676,0.00004808906,0.004161269,0.06753106,0.00001909596,0.238531,0.5382079,0.1248286],"study_design_scores_gemma":[0.002006906,0.002955608,0.0005031367,0.00859326,0.0002793022,0.0001853029,0.002462306,0.03442411,0.00001412417,0.1172525,0.8297992,0.001524283],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003179446,0.08810246,0.7718675,0.1156287,0.002497791,0.006705919,0.006404998,0.0001705213,0.00830421],"genre_scores_gemma":[0.4866223,0.1402584,0.1809207,0.05902343,0.01065049,0.0006084149,0.02075727,0.0009003415,0.1002586],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5909468,"threshold_uncertainty_score":0.9998659,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4213962004954483,"score_gpt":0.4654224889437468,"score_spread":0.04402628844829853,"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."}}