{"id":"W2483382222","doi":"10.4018/978-1-4666-2455-9.ch042","title":"Heterogeneous Text and Numerical Data Mining with Possible Applications in Business and Financial Sectors","year":2012,"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; Data science; Data type; Semantics (computer science); Qualitative property; Data processing; Financial sector; Database; Finance; Business; 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":[0.00008949297,0.0002912302,0.000303801,0.00006764294,0.0001435041,0.0002133595,0.0008636428,0.0001659226,0.00000225986],"category_scores_gemma":[0.0000077835,0.0002590934,0.00001578561,0.00008880811,0.0001265537,0.0001990824,0.0009735107,0.0001500615,0.000009047633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004449102,"about_ca_system_score_gemma":0.0001711569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001528558,"about_ca_topic_score_gemma":0.000145061,"domain_scores_codex":[0.9985002,0.000008543238,0.0002388602,0.0007755986,0.0001904009,0.000286393],"domain_scores_gemma":[0.9984955,0.00004435607,0.0001351198,0.001107436,0.00005398438,0.000163648],"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":[0.000007470104,0.00003299068,0.0006047662,0.00004278864,0.00002544046,0.00002400021,0.0001630637,0.000004466241,0.000004577675,0.689157,0.0003469558,0.3095864],"study_design_scores_gemma":[0.003683834,0.000602496,0.03886378,0.001684636,0.0005500168,0.003681052,0.0001050132,0.02419172,0.00007656903,0.1109043,0.808953,0.006703603],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003877118,0.004943026,0.5163559,0.0003993431,0.0002845125,0.002012957,0.002923118,0.0004727929,0.4687312],"genre_scores_gemma":[0.541754,0.0001593188,0.4436037,0.001009071,0.001246019,0.00046806,0.0005658761,0.0001950821,0.01099888],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.808606,"threshold_uncertainty_score":0.9999861,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0238077634119469,"score_gpt":0.247941566638982,"score_spread":0.2241338032270351,"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."}}