{"id":"W3198016176","doi":"10.1007/s13278-021-00784-6","title":"Improving e-commerce product recommendation using semantic context and sequential historical purchases","year":2021,"lang":"en","type":"article","venue":"Social Network Analysis and Mining","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Information retrieval; Context (archaeology); Semantics (computer science); Recommender system; Collaborative filtering; Similarity (geometry); Personalization; Cluster analysis; Semantic similarity; Process (computing); Metadata; Preprocessor; Matching (statistics); Natural language processing; Artificial intelligence; World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000572888,0.0001398788,0.0004039007,0.0001103324,0.0005957352,0.0003068831,0.0001115424,0.00006494861,0.000008677941],"category_scores_gemma":[0.0000299022,0.0001416592,0.0001243687,0.0008460141,0.000025951,0.0002824219,0.0002587364,0.0001119528,1.835154e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001072526,"about_ca_system_score_gemma":0.0000465639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000867988,"about_ca_topic_score_gemma":0.0003897742,"domain_scores_codex":[0.9985987,0.0002189645,0.0003262282,0.0004720273,0.0001223824,0.0002617227],"domain_scores_gemma":[0.9993932,0.0000745518,0.000208157,0.0001620502,0.00009467309,0.00006737872],"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":[0.000005308691,0.00004648027,0.02855223,0.00004892269,0.0006658223,0.00002187585,0.003060092,0.00003872633,0.000932328,0.003740786,0.002182141,0.9607053],"study_design_scores_gemma":[0.001615267,0.0002320114,0.01723065,0.0002430061,0.00359789,0.0002271327,0.004304765,0.8972244,0.001832719,0.003350991,0.0677964,0.002344802],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1090448,0.001955495,0.8862604,0.001946615,0.0003823382,0.00009661481,0.000001233191,0.0001020818,0.0002103985],"genre_scores_gemma":[0.9641332,0.00008071533,0.03486547,0.0002198856,0.0005563196,0.000006198848,0.0000124851,0.000008990115,0.000116736],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9583605,"threshold_uncertainty_score":0.5776696,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0382843593755317,"score_gpt":0.2797074508244983,"score_spread":0.2414230914489666,"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."}}