{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01326227,0.001057672,0.002093841,0.001751813,0.0006425268,0.001304313,0.001742462,0.0005228331,0.00004166773],"category_scores_gemma":[0.001389337,0.001100157,0.0004662374,0.003424312,0.0002707185,0.001364654,0.0007997045,0.0008573612,0.00004210006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007034443,"about_ca_system_score_gemma":0.00010126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00164105,"about_ca_topic_score_gemma":0.0008610134,"domain_scores_codex":[0.9876199,0.0007149472,0.005192877,0.002613261,0.002152349,0.001706716],"domain_scores_gemma":[0.9922695,0.001252944,0.003835683,0.001538968,0.001012848,0.00009007349],"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":[0.0008881866,0.001154329,0.1022251,0.008702284,0.0003997185,0.0002995177,0.005632323,0.2028874,0.0006100513,0.05549717,0.001780158,0.6199238],"study_design_scores_gemma":[0.002337877,0.000208735,0.07854231,0.008907323,0.000220408,0.0001086895,0.01491652,0.5119154,0.001069793,0.002623765,0.3770591,0.002090134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5136299,0.007522586,0.4650364,0.000116905,0.006221438,0.004712586,0.00008997499,0.0001318167,0.002538446],"genre_scores_gemma":[0.9778098,0.007099732,0.006557702,0.0001069664,0.0003410958,0.0009419832,0.00005748283,0.000128438,0.006956764],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6178336,"threshold_uncertainty_score":0.9997324,"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."}}