{"id":"W2563000706","doi":"10.5430/air.v6n1p80","title":"Can machine learning techniques predict customer dissatisfaction? A feasibility study for the automotive industry","year":2016,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Automotive industry; Competitor analysis; Computer science; Customer satisfaction; Service (business); Support vector machine; Artificial intelligence; Machine learning; Marketing; Business; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003521146,0.0001506592,0.000150304,0.0003291699,0.0009823751,0.0003559393,0.0003609826,0.0001116956,0.0005502204],"category_scores_gemma":[0.00169155,0.00008724279,0.00007342309,0.0008792495,0.000277463,0.0005653509,0.0002080616,0.0006235087,0.0002335696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001840604,"about_ca_system_score_gemma":0.00005846825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003863975,"about_ca_topic_score_gemma":0.003812645,"domain_scores_codex":[0.9979408,0.0001297773,0.0003609128,0.0004218234,0.0006650565,0.0004816342],"domain_scores_gemma":[0.9979712,0.0008160918,0.0001079125,0.000308281,0.0007687511,0.00002778327],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000438275,0.0007379484,0.3375542,0.00005673007,0.00008973114,0.000006525108,0.001043627,0.00004740656,0.006358735,0.01131941,0.001148649,0.6411988],"study_design_scores_gemma":[0.001357313,0.002170828,0.3638181,0.0006189328,0.0004869319,0.0000112361,0.1600787,0.0531284,0.1756312,0.1797971,0.06033449,0.002566702],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9590732,0.00004842755,0.01719443,0.01526286,0.0004652077,0.005257125,0.00002731807,0.0004416427,0.002229729],"genre_scores_gemma":[0.997899,0.00001440593,0.00003862259,0.0001057347,0.0007403886,0.0004196003,0.000007986191,0.00002569837,0.0007485424],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6386321,"threshold_uncertainty_score":0.7555734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2094813873278795,"score_gpt":0.4236811888324536,"score_spread":0.2141998015045742,"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."}}