{"id":"W4312812430","doi":"10.1007/978-3-031-22695-3_44","title":"Optimizing the Feature Set for Machine Learning Charitable Predictions","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Nonprofit Sector and Volunteering","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Acadia University","funders":"","keywords":"Feature (linguistics); Computer science; Machine learning; Artificial intelligence; Set (abstract data type); Random forest; Focus (optics); Decision tree; Measure (data warehouse); Training set; Data mining","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":[0.001792878,0.0008868327,0.001161706,0.001112818,0.0005636855,0.00114532,0.001722006,0.001702795,0.00709866],"category_scores_gemma":[0.006018946,0.0004376557,0.0007758,0.001276777,0.0004441724,0.001709677,0.001035759,0.002141306,0.00208643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009031111,"about_ca_system_score_gemma":0.001093071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005034895,"about_ca_topic_score_gemma":0.006165087,"domain_scores_codex":[0.9993062,0.0002650979,0.0000295987,0.0001391665,0.0001335665,0.0001263909],"domain_scores_gemma":[0.9973207,0.001941159,0.00009786706,0.0002460809,0.0003263474,0.00006789748],"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":[0.0003330497,0.0005389907,0.003891819,0.00009783527,0.000080378,0.0000852208,0.00003536027,0.449593,0.001905612,0.006332816,0.02977771,0.5073281],"study_design_scores_gemma":[0.00001144897,0.00002428082,0.0003218726,0.000008912147,0.000006691206,0.00001159532,0.000008337321,0.993887,0.0006229121,0.004686057,0.000406398,0.000004437014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1824257,0.00144894,0.7895482,0.002646057,0.000403175,0.0002679477,0.00270447,0.006974698,0.01358072],"genre_scores_gemma":[0.808331,0.0003092597,0.1696029,0.000385835,0.0003298598,0.0003558512,0.005691746,0.0004054406,0.01458808],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00709866,"threshold_uncertainty_score":0.02374732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02915454453663124,"score_gpt":0.2864929065467932,"score_spread":0.2573383620101619,"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."}}