{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T23:07:39Z","timestamp":1773616059817,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,15]]},"DOI":"10.1145\/3768292.3770372","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:24:26Z","timestamp":1763105066000},"page":"62-70","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Financial Statement Fraud Detection with a Categorical-to-Numerical Data Representation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8119-3740","authenticated-orcid":false,"given":"Tuna","family":"Alaygut","sequence":"first","affiliation":[{"name":"Artificial Intelligence and Data Engineering, Ozyegin University, Istanbul, Select State, Turkiye"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9186-0270","authenticated-orcid":false,"given":"Emre","family":"Sefer","sequence":"additional","affiliation":[{"name":"Artificial Intelligence and Data Engineering, Ozyegin University, Istanbul, Select State, Turkiye"}]}],"member":"320","published-online":{"date-parts":[[2025,11,14]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3704323.3704378"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16826"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Yang Bao Bin Ke Bin Li Y\u00a0Julia Yu and Jie Zhang. 2020. Detecting accounting fraud in publicly traded US firms using a machine learning approach. Journal of Accounting Research 58 1 (2020) 199\u2013235.","DOI":"10.1111\/1475-679X.12292"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Selinay Cetin and Emre Sefer. 2025. A Graphlet-based Explanation Generator for Graph Neural Networks Over Biological Datasets. CURRENT BIOINFORMATICS 20 (2025).","DOI":"10.2174\/0115748936355418250114104026"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_3_1_8_2","unstructured":"Yury Gorishniy Ivan Rubachev Valentin Khrulkov and Artem Babenko. 2021. Revisiting deep learning models for tabular data. Advances in neural information processing systems 34 (2021) 18932\u201318943."},{"key":"e_1_3_3_1_9_2","unstructured":"Margherita Grandini Enrico Bagli and Giorgio Visani. 2020. Metrics for multi-class classification: an overview. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2008.05756 (2020)."},{"key":"e_1_3_3_1_10_2","unstructured":"Songqiao Han Xiyang Hu Hailiang Huang Minqi Jiang and Yue Zhao. 2022. Adbench: Anomaly detection benchmark. Advances in neural information processing systems 35 (2022) 32142\u201332159."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Songlei Jian Guansong Pang Longbing Cao Kai Lu and Hang Gao. 2018. Cure: Flexible categorical data representation by hierarchical coupling learning. IEEE Transactions on Knowledge and Data Engineering 31 5 (2018) 853\u2013866.","DOI":"10.1109\/TKDE.2018.2848902"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467304"},{"key":"e_1_3_3_1_13_2","unstructured":"Guolin Ke Qi Meng Thomas Finley Taifeng Wang Wei Chen Weidong Ma Qiwei Ye and Tie-Yan Liu. 2017. Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449989"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Ivan Lopez-Arevalo Edwin Aldana-Bobadilla Alejandro Molina-Villegas Hiram Galeana-Zapi\u00e9n Victor Mu\u00f1iz-Sanchez and Saul Gausin-Valle. 2020. A memory-efficient encoding method for processing mixed-type data on machine learning. Entropy 22 12 (2020) 1391.","DOI":"10.3390\/e22121391"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Xuting Mao Mingxi Liu and Yinghui Wang. 2022. Using GNN to detect financial fraud based on the related party transactions network. Procedia Computer Science 214 (2022) 351\u2013358.","DOI":"10.1016\/j.procs.2022.11.185"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339541"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23038-7_21"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Kedar Potdar Taher\u00a0S Pardawala and Chinmay\u00a0D Pai. 2017. A comparative study of categorical variable encoding techniques for neural network classifiers. International journal of computer applications 175 4 (2017) 7\u20139.","DOI":"10.5120\/ijca2017915495"},{"key":"e_1_3_3_1_20_2","unstructured":"Liudmila Prokhorenkova Gleb Gusev Aleksandr Vorobev Anna\u00a0Veronika Dorogush and Andrey Gulin. 2018. CatBoost: unbiased boosting with categorical features. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Pediredla Ravisankar Vadlamani Ravi G\u00a0Raghava Rao and Indranil Bose. 2011. Detection of financial statement fraud and feature selection using data mining techniques. Decision support systems 50 2 (2011) 491\u2013500.","DOI":"10.1016\/j.dss.2010.11.006"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Frank Rosenblatt. 1958. The perceptron: a probabilistic model for information storage and organization in the brain. Psychological review 65 6 (1958) 386.","DOI":"10.1037\/h0042519"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Emre Sefer. 2021. Hi\u2013C interaction graph analysis reveals the impact of histone modifications in chromatin shape. Applied Network Science 6 1 (2021) 54.","DOI":"10.1007\/s41109-021-00396-1"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Emre Sefer. 2022. BioCode: A Data-Driven Procedure to Learn the Growth of Biological Networks. IEEE\/ACM Transactions on Computational Biology and Bioinformatics 19 6 (2022) 3103\u20133113.","DOI":"10.1109\/TCBB.2022.3165092"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Emre Sefer. 2022. ProbC: joint modeling of epigenome and transcriptome effects in 3D genome. BMC genomics 23 1 (2022) 287.","DOI":"10.1186\/s12864-022-08498-5"},{"key":"e_1_3_3_1_26_2","first-page":"137","volume-title":"International Conference on Complex Networks and Their Applications","author":"Sefer Emre","year":"2024","unstructured":"Emre Sefer. 2024. PageRank-Based Unsupervised Deep Vertex Representations for Anti-money Laundering Detection. In International Conference on Complex Networks and Their Applications. Springer, 137\u2013149."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611978520.6"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","unstructured":"Emre Sefer and Carl Kingsford. 2021. Metric Labeling and Semimetric Embedding for Protein Annotation Prediction. Journal of Computational Biology 28 5 (2021) 514\u2013525. 10.1089\/cmb.2020.0425 arXiv:10.1089\/cmb.2020.0425 PMID: 33370163.","DOI":"10.1089\/cmb.2020.0425"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Chris Seiffert Taghi\u00a0M Khoshgoftaar Jason Van\u00a0Hulse and Amri Napolitano. 2009. RUSBoost: A hybrid approach to alleviating class imbalance. IEEE transactions on systems man and cybernetics-part A: systems and humans 40 1 (2009) 185\u2013197.","DOI":"10.1109\/TSMCA.2009.2029559"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939704"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357925"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Necla\u00a0N Soylu and Emre Sefer. 2024. DeepPTM: protein post-translational modification prediction from protein sequences by combining deep protein language model with vision transformers. Current Bioinformatics 19 9 (2024) 810\u2013824.","DOI":"10.2174\/0115748936283134240109054157"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3124749.3124754"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450078"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"crossref","unstructured":"Weiwei Wang Stefano Bromuri and Michel Dumontier. 2023. Graph based categorical embedding. ESANN.","DOI":"10.14428\/esann\/2023.ES2023-32"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583373"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26702"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974010.6"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489605"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Wei Zhou and Gaurav Kapoor. 2011. Detecting evolutionary financial statement fraud. Decision support systems 50 3 (2011) 570\u2013575.","DOI":"10.1016\/j.dss.2010.08.007"},{"key":"e_1_3_3_1_41_2","unstructured":"Wenbin Zhu Runwen Qiu and Ying Fu. 2024. Comparative study on the performance of categorical variable encoders in classification and regression tasks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.09682 (2024)."}],"event":{"name":"ICAIF '25: 6th ACM International Conference on AI in Finance","location":"Singapore Singapore","acronym":"ICAIF '25"},"container-title":["Proceedings of the 6th ACM International Conference on AI in Finance"],"original-title":[],"deposited":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:27:06Z","timestamp":1763105226000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3768292.3770372"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"references-count":40,"alternative-id":["10.1145\/3768292.3770372","10.1145\/3768292"],"URL":"https:\/\/doi.org\/10.1145\/3768292.3770372","relation":{},"subject":[],"published":{"date-parts":[[2025,11,14]]},"assertion":[{"value":"2025-11-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}