{"id":"W3000502290","doi":"10.2478/wsbjbf-2019-0022","title":"Machine learning model development for predicting road transport GHG emissions in Canada","year":2019,"lang":"en","type":"article","venue":"WSB Journal of Business and Finance","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Decision tree; Artificial neural network; Greenhouse gas; Multilayer perceptron; Multinomial logistic regression; Machine learning; Perceptron; Boosting (machine learning); Computer science; Gradient boosting; Random forest; Artificial intelligence; Predictive modelling; Logistic regression","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003314172,0.00007323059,0.0001535072,0.00002015107,0.0000960511,0.000005955069,0.00007753772,0.00002369505,0.00001272531],"category_scores_gemma":[0.00004017216,0.00006167727,0.00001654303,0.0001087515,0.00001332798,0.0001315774,0.00002156053,0.0001481961,4.357595e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001681964,"about_ca_system_score_gemma":0.0001992192,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.05712975,"about_ca_topic_score_gemma":0.02533936,"domain_scores_codex":[0.9992617,0.000007677419,0.0003088952,0.0001005429,0.0001652423,0.0001559893],"domain_scores_gemma":[0.9996901,0.0000259511,0.0001888119,0.00003931314,0.00002222198,0.00003358628],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000264943,0.00001179616,0.639708,0.00004903772,0.000002269803,0.000005390496,0.000446472,0.3092082,0.0002203635,0.000003986805,0.000008727047,0.05030926],"study_design_scores_gemma":[0.0004829993,0.00002190937,0.7222251,0.0005396141,0.000004080367,0.00001955627,0.0001423454,0.2722219,0.0001617478,0.00003865727,0.00402414,0.0001179931],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9917534,0.0002340867,0.00753881,0.0001097124,0.0001282797,0.00005429577,0.000002474585,0.000002124055,0.0001768282],"genre_scores_gemma":[0.9932439,0.0001348747,0.006219351,0.00001957911,0.00002702875,0.000001820629,0.000001259487,0.000006747371,0.0003454658],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08251701,"threshold_uncertainty_score":0.9924456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01653112400540131,"score_gpt":0.2087621720581983,"score_spread":0.192231048052797,"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."}}