{"id":"W3198845996","doi":"10.1002/isaf.1500","title":"Machine learning for financial transaction classification across companies using character‐level word embeddings of text fields","year":2021,"lang":"en","type":"article","venue":"Intelligent systems in accounting, finance and management/Intelligent systems in accounting, finance & management","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"PricewaterhouseCoopers (Canada)","funders":"","keywords":"Character (mathematics); Word (group theory); Natural language processing; Database transaction; Computer science; Artificial intelligence; Business; Finance; Linguistics; Mathematics; Database","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":[0.001369004,0.0007652882,0.0005814637,0.002103823,0.0003530039,0.0009885964,0.0006216514,0.0008225188,0.001614694],"category_scores_gemma":[0.003939257,0.0002087843,0.0004882314,0.001673304,0.0002691715,0.002200393,0.0007381787,0.001083029,0.001148332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005441085,"about_ca_system_score_gemma":0.0005469666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002515423,"about_ca_topic_score_gemma":0.002580983,"domain_scores_codex":[0.9993537,0.0002098721,0.00008958233,0.0001937148,0.00007625096,0.00007681573],"domain_scores_gemma":[0.997572,0.001453512,0.0002763546,0.0001989672,0.0004011553,0.00009805186],"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":[0.0004380214,0.0006276378,0.02562648,0.0001352514,0.0001157237,0.0001872345,0.0001951055,0.06205982,0.009549924,0.002967346,0.006532861,0.8915647],"study_design_scores_gemma":[0.00001275761,0.00005681831,0.002586318,0.00001500268,0.00001094668,0.00003477048,0.00009113937,0.9903537,0.002623738,0.003506905,0.0006980731,0.000009947868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7088498,0.001242973,0.2801411,0.00101247,0.0002964492,0.00019516,0.001432627,0.003988398,0.002841027],"genre_scores_gemma":[0.9120885,0.0001662658,0.08356521,0.00007829052,0.00006813899,0.00008616228,0.002073035,0.00004460851,0.001829773],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002515423,"threshold_uncertainty_score":0.007240057,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1093787751483146,"score_gpt":0.3781065978509657,"score_spread":0.2687278227026512,"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."}}