{"id":"W4396982473","doi":"10.2139/ssrn.4830661","title":"Generating Practical Last-mile Delivery Routes using a Data-informed Insertion Heuristic","year":2024,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Transportation Planning and Optimization","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Travelling salesman problem; Computer science; Operations research; Heuristic; Leverage (statistics); Backtracking; Quality (philosophy); Last mile (transportation); Customer satisfaction; Operations management; Mile; Artificial intelligence; Marketing; Business; Engineering; Algorithm; Geography","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":[0.001393038,0.001720658,0.001817092,0.001843762,0.0009250402,0.001388372,0.002428897,0.00313979,0.009950464],"category_scores_gemma":[0.006572878,0.001750523,0.00140857,0.002297122,0.001039524,0.001812813,0.001466475,0.002013124,0.001144872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001776797,"about_ca_system_score_gemma":0.003460445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01476357,"about_ca_topic_score_gemma":0.01509141,"domain_scores_codex":[0.9993559,0.000222458,0.00003089825,0.000146467,0.0001075294,0.0001368192],"domain_scores_gemma":[0.9955196,0.003406263,0.0001761039,0.0002779705,0.000431798,0.0001882957],"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":[0.0001281516,0.00008502816,0.0002957699,0.00006926367,0.00001344928,0.0000912052,0.0000440981,0.9779611,0.0003954066,0.001858302,0.0009746858,0.01808348],"study_design_scores_gemma":[0.00004065575,0.00003533591,0.00004444492,0.000006122088,0.000007832644,0.00001092435,0.0000325174,0.997347,0.0002495064,0.001977848,0.0002427283,0.000005043192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1787542,0.000511265,0.7986601,0.000928508,0.0001748925,0.0006335435,0.001279245,0.003101791,0.01595653],"genre_scores_gemma":[0.6164973,0.0001352945,0.3780158,0.000137114,0.00003368992,0.0003923876,0.001090952,0.0002863644,0.003411238],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01476357,"threshold_uncertainty_score":0.03328758,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04577192064329817,"score_gpt":0.3549527072568466,"score_spread":0.3091807866135484,"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."}}