{"id":"W3204758977","doi":"10.48550/arxiv.2109.14097","title":"How Much Data Analytics is Enough? The ROI of Machine Learning Classification and its Application to Requirements Dependency Classification","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Dependency (UML); Return on investment; Analytics; Artificial intelligence; Selection (genetic algorithm); Region of interest; Software; Machine learning; 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":[0.02689457,0.001114984,0.001359267,0.003141683,0.0008337394,0.005486391,0.001308805,0.001704751,0.001126486],"category_scores_gemma":[0.1136151,0.000386059,0.0007819329,0.003662532,0.001739744,0.009654511,0.002127831,0.002712851,0.001011354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001681656,"about_ca_system_score_gemma":0.001812998,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002183438,"about_ca_topic_score_gemma":0.003414414,"domain_scores_codex":[0.9813763,0.01041163,0.001158913,0.001656457,0.004738778,0.0006579998],"domain_scores_gemma":[0.8573274,0.1099572,0.008624624,0.01334102,0.009184455,0.00156533],"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":[0.001640952,0.0004674724,0.1709723,0.0008745561,0.0004108116,0.0002625445,0.001116826,0.05416415,0.01070586,0.02881945,0.01277723,0.7177878],"study_design_scores_gemma":[0.0001848698,0.00103325,0.08195507,0.001070069,0.0004426359,0.001013252,0.003435455,0.6394223,0.04571796,0.1884256,0.03707409,0.0002255449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5358698,0.00993621,0.3912856,0.03464859,0.0003705252,0.000284728,0.003318606,0.002416844,0.02186911],"genre_scores_gemma":[0.9079836,0.000873866,0.0879517,0.0006618101,0.0001947733,0.00007505361,0.001452212,0.0002316526,0.0005753721],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02689457,"threshold_uncertainty_score":0.1422338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2135954742186379,"score_gpt":0.2580230380897199,"score_spread":0.04442756387108196,"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."}}