{"id":"W2995930425","doi":"","title":"A Hybrid Recommendation Method Based on Feature for Offline Book Personalization","year":2019,"lang":"en","type":"article","venue":"Journal of Computers","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Collaborative filtering; Computer science; Word2vec; Personalization; Preference; Similarity (geometry); Recommender system; Feature (linguistics); Information retrieval; Order (exchange); Artificial intelligence; Data mining; World Wide Web; Statistics; Mathematics; Business; Embedding","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":[0.0004300612,0.00008824457,0.0001528127,0.0002948983,0.0000484396,0.0001261963,0.00009075129,0.00002526191,0.0001743491],"category_scores_gemma":[0.00002435427,0.00007542691,0.0001236969,0.0001107698,0.000004066827,0.0006677812,0.00001091651,0.00008741648,0.00002352579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005240259,"about_ca_system_score_gemma":0.00001961899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000265262,"about_ca_topic_score_gemma":4.834617e-7,"domain_scores_codex":[0.9994061,0.00001534368,0.00021222,0.00009412252,0.0001798143,0.00009242227],"domain_scores_gemma":[0.9991567,0.00009698539,0.000450518,0.00005798631,0.0002277825,0.000009985923],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001596806,0.0003568264,0.003091799,0.0006375784,0.0001455404,0.000008618992,0.0001731059,0.03775791,0.002631483,0.002961838,0.7759952,0.1746433],"study_design_scores_gemma":[0.002057002,0.0000943844,0.001085451,0.0001025761,0.00004806218,0.000005812127,0.00004753379,0.6825562,0.0001717465,0.0002135876,0.3135133,0.0001043906],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01876122,0.00002828602,0.9650419,0.01231673,0.00191205,0.0003435548,0.0000030413,0.00002428149,0.00156892],"genre_scores_gemma":[0.7768691,0.00001895822,0.1200288,0.09381644,0.006739506,0.00001101154,0.0005560581,0.00009306687,0.001867026],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8450131,"threshold_uncertainty_score":0.307582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0144623848386115,"score_gpt":0.2656781941869277,"score_spread":0.2512158093483162,"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."}}