{"id":"W3202591630","doi":"10.1145/3468227","title":"Factorizing Historical User Actions for Next-Day Purchase Prediction","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on the Web","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Recommender system; Leverage (statistics); Collaborative filtering; Markov chain; Machine learning; Database transaction; Bayesian probability; Artificial intelligence; Database","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":[0.000306755,0.0001325437,0.0001397945,0.00009251787,0.0005598406,0.0001873489,0.0006031848,0.00009245936,0.00005178374],"category_scores_gemma":[0.00006404218,0.0001018716,0.0001901041,0.0003570761,0.00001429212,0.0004833216,0.00001663551,0.0002428127,0.00001706312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003063965,"about_ca_system_score_gemma":0.00009896245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004061075,"about_ca_topic_score_gemma":0.00003644358,"domain_scores_codex":[0.9989109,0.0001184946,0.0002319393,0.0003314522,0.0001904734,0.0002167618],"domain_scores_gemma":[0.9982781,0.0004519187,0.000060284,0.001027894,0.0001076354,0.00007411266],"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":[0.00004919884,0.001739132,0.0001657285,0.0001105549,0.0005915096,0.00002912097,0.003900612,0.000507862,0.08469467,0.1118517,0.1290582,0.6673017],"study_design_scores_gemma":[0.0002975184,0.000144206,0.00008484253,0.00003422198,0.00003267183,0.0000474315,0.0001396419,0.006775537,0.03682831,0.006475403,0.9489449,0.0001953075],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006047355,0.00008557561,0.9774265,0.01872201,0.001970109,0.0002903716,0.00002674594,0.0004252497,0.0004486783],"genre_scores_gemma":[0.9502428,0.0001660685,0.04334782,0.0005992011,0.0002435274,0.0005712483,0.000006427227,0.00002827587,0.004794589],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9496381,"threshold_uncertainty_score":0.4305898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09274718359665297,"score_gpt":0.2785687719892228,"score_spread":0.1858215883925698,"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."}}