{"id":"W4406043290","doi":"10.18280/ijsse.140613","title":"Phishing Detection Using Random Forest-Based Weighted Bootstrap Sampling and LASSO+ Feature Selection","year":2024,"lang":"en","type":"article","venue":"International Journal of Safety and Security Engineering","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Random forest; Feature selection; Lasso (programming language); Computer science; Selection (genetic algorithm); Sampling (signal processing); Feature (linguistics); Artificial intelligence; Statistics; Data mining; Machine learning; Pattern recognition (psychology); Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003626897,0.0009726291,0.001990305,0.001481165,0.0008540525,0.0007494853,0.001346704,0.001058104,0.001229825],"category_scores_gemma":[0.006951527,0.0003475015,0.001399049,0.001064426,0.0004122395,0.0008499933,0.0009158088,0.00119603,0.0007690518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002630454,"about_ca_system_score_gemma":0.001025899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003371312,"about_ca_topic_score_gemma":0.004283233,"domain_scores_codex":[0.9980912,0.0007856918,0.0001092675,0.0003826804,0.0003654312,0.0002657956],"domain_scores_gemma":[0.9971301,0.001385407,0.0002111246,0.0003749849,0.0007607869,0.0001376468],"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":[0.001759019,0.001423822,0.02441873,0.0002427757,0.0005413322,0.0004433022,0.0001956593,0.2048926,0.01456129,0.002303854,0.01284674,0.7363709],"study_design_scores_gemma":[0.00002916,0.00006661285,0.001372066,0.00000539323,0.00003624196,0.00005678533,0.00001517293,0.996458,0.0009196725,0.0007484668,0.0002834178,0.00000895284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1508407,0.0005467916,0.8433007,0.0002508274,0.000124197,0.0002224907,0.0004350013,0.003395137,0.000884205],"genre_scores_gemma":[0.7512113,0.0001319688,0.2443487,0.0001632482,0.0001629958,0.0002319673,0.002101189,0.0001528831,0.001495881],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003626897,"threshold_uncertainty_score":0.01918107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01137422995268639,"score_gpt":0.2443478693589702,"score_spread":0.2329736394062839,"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."}}