{"id":"W4322741464","doi":"10.1007/s00778-023-00787-z","title":"Leveraging user itinerary to improve personalized deep matching at Fliggy","year":2023,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Science Foundation of Guangxi Province; National Natural Science Foundation of China","keywords":"Computer science; Matching (statistics); Weighting; Benchmark (surveying); Artificial intelligence; Machine learning; 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":[0.001346174,0.0001392737,0.0001725438,0.0001665196,0.00062164,0.0004836429,0.00108042,0.00003678741,0.00004171755],"category_scores_gemma":[0.0000192891,0.00008888806,0.0001233178,0.0003957021,0.00001559962,0.0003495732,0.0006314195,0.0002999381,0.0002126585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009819672,"about_ca_system_score_gemma":0.0000374553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004836356,"about_ca_topic_score_gemma":0.000004489377,"domain_scores_codex":[0.9985888,0.0001646916,0.0002824929,0.000218771,0.0003477855,0.0003974307],"domain_scores_gemma":[0.9991667,0.000116271,0.0001250459,0.0003880953,0.00005427164,0.000149619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000857437,0.00009286198,0.002537763,0.00009132409,0.0003972641,0.0009790786,0.08958524,0.001030874,0.1288319,0.05105844,0.3463054,0.3790041],"study_design_scores_gemma":[0.003307039,0.000618618,0.01545781,0.0007293791,0.00006431703,0.01070451,0.004210846,0.09693324,0.04172163,0.1494863,0.6744457,0.002320603],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3936732,0.0002117512,0.5777031,0.02338032,0.00165199,0.0002359468,0.00000128388,0.0005486315,0.002593835],"genre_scores_gemma":[0.962209,0.00008681321,0.02598646,0.00330637,0.0009356843,0.00003074424,0.0000010142,0.00003620322,0.007407641],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5685359,"threshold_uncertainty_score":0.4781215,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02644243369677945,"score_gpt":0.2688672081487491,"score_spread":0.2424247744519696,"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."}}