{"id":"W4256184506","doi":"10.4018/978-1-60960-126-3.ch004","title":"Heterogeneous Text and Numerical Data Mining with Possible Applications in Business and Financial Sectors","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Semantics (computer science); Data type; Data science; Data processing; Qualitative property; Data modeling; Data mining; Database; Programming language; Machine learning","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00007485828,0.0002937039,0.0003078001,0.00007212977,0.0001369499,0.0001925248,0.00098121,0.0001659872,0.000002646209],"category_scores_gemma":[0.000007716943,0.0002614821,0.00001616789,0.0000863456,0.0001420552,0.0001574577,0.0009882455,0.0001471926,0.000008295485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003606436,"about_ca_system_score_gemma":0.0002009436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002774356,"about_ca_topic_score_gemma":0.0002309229,"domain_scores_codex":[0.9984292,0.00000801402,0.0002460871,0.0009043267,0.0001683189,0.0002440193],"domain_scores_gemma":[0.9984583,0.00003451639,0.0001394428,0.001169667,0.00006092666,0.0001371904],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009149315,0.00002792165,0.0003221229,0.0000351598,0.00002410204,0.00004250393,0.0001822327,0.000002449003,0.000002602641,0.808742,0.0003276305,0.1902821],"study_design_scores_gemma":[0.004224895,0.001036064,0.03301099,0.002144518,0.0005423523,0.003878187,0.00009805873,0.02122506,0.00009847966,0.3724385,0.5537846,0.007518264],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.001930138,0.001275915,0.4141533,0.0001589473,0.0001549133,0.00123177,0.001674608,0.0003038867,0.5791165],"genre_scores_gemma":[0.4559009,0.0001570951,0.5213767,0.001173604,0.0008607012,0.0005636856,0.0005334236,0.0002330283,0.01920087],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5599156,"threshold_uncertainty_score":0.9999837,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02756939377203025,"score_gpt":0.2426782168533207,"score_spread":0.2151088230812905,"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."}}