{"id":"W3155477400","doi":"10.1145/3442381.3449803","title":"Itinerary-aware Personalized Deep Matching at Fliggy","year":2021,"lang":"en","type":"article","venue":"","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Matching (statistics); Mathematics; Statistics","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":[0.0003803157,0.0009053602,0.0009143536,0.0004998096,0.0004811766,0.0005734163,0.001723086,0.00104975,0.003313056],"category_scores_gemma":[0.00123588,0.00036715,0.000662152,0.0007265522,0.0003456496,0.002329252,0.001202207,0.001402332,0.0009085923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001078148,"about_ca_system_score_gemma":0.001001712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02438278,"about_ca_topic_score_gemma":0.03809888,"domain_scores_codex":[0.9997196,0.00003024881,0.00001014392,0.0001064468,0.00005479274,0.00007872124],"domain_scores_gemma":[0.9997486,0.00005836911,0.0000276647,0.00007077058,0.00005575747,0.00003880997],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008947159,0.0008054309,0.009849701,0.0002196693,0.0002579422,0.0004103938,0.0002551651,0.289893,0.01830172,0.005608344,0.02850557,0.6449984],"study_design_scores_gemma":[0.00002118735,0.00009722388,0.001059948,0.000009080285,0.00002336381,0.0000630509,0.00003407035,0.9907303,0.00341657,0.002940432,0.001593287,0.00001146455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4095204,0.00183928,0.5617713,0.0008627299,0.000275541,0.0002162955,0.002356574,0.0118536,0.01130434],"genre_scores_gemma":[0.9024994,0.0002569285,0.08427963,0.0005419482,0.00003982969,0.00008715322,0.002937926,0.000165346,0.009191855],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02438278,"threshold_uncertainty_score":0.0484817,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0177604839003189,"score_gpt":0.2495598023646967,"score_spread":0.2317993184643778,"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."}}