{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T06:33:27Z","timestamp":1777876407190,"version":"3.51.4"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032180698","type":"print"},{"value":"9783032180704","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-18070-4_11","type":"book-chapter","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T22:22:07Z","timestamp":1777587727000},"page":"170-185","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Tabular Data Augmentation for\u00a0Database Scalability Testing \u2013 A Case Study with\u00a0Medical Insurance Claims Analytics Workloads \u2013"],"prefix":"10.1007","author":[{"given":"Taro","family":"Fujimoto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Fujiwara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6032-1584","authenticated-orcid":false,"given":"Jumpei","family":"Sato","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5746-1743","authenticated-orcid":false,"given":"Yuto","family":"Hayamizu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0618-4157","authenticated-orcid":false,"given":"Kazuo","family":"Goda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,1]]},"reference":[{"key":"11_CR1","unstructured":"Borisov, V., Se\u00dfler, K., Leemann, T., Pawelczyk, M., Kasneci, G.: Language models are realistic tabular data generators. arXiv preprint arXiv:2210.06280 (2022)"},{"key":"11_CR2","unstructured":"Ceritli, T., Ghosheh, G.O., Chauhan, V.K., Zhu, T., Creagh, A.P., Clifton, D.A.: Synthesizing mixed-type electronic health records using diffusion models. arXiv preprint arXiv:2302.14679 (2023)"},{"key":"11_CR3","unstructured":"Croesus Lab: RC-TGAN GitHub Repository. https:\/\/github.com\/croesuslab\/RCTGAN (2023)"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Goda, K., Hayamizu, Y., Nishikawa, N., Fujiwara, S.: 4mbench: performance benchmark of manufacturing business database. In: Proceedings of the TPCTC, pp. 94\u2013109 (2022)","DOI":"10.1007\/978-3-031-29576-8_7"},{"issue":"12","key":"11_CR5","doi-asserted-by":"publisher","first-page":"3489","DOI":"10.14778\/3415478.3415571","volume":"13","author":"K Goda","year":"2020","unstructured":"Goda, K., Hayamizu, Y., Yamada, H., Kitsuregawa, M.: Out-of-order execution of database queries. Proc. VLDB Endow. 13(12), 3489\u20133501 (2020)","journal-title":"Proc. VLDB Endow."},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Gosain, A., Sardana, S.: Handling class imbalance problem using oversampling techniques: a review. In: Proceedings of the 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), pp. 79\u201385 (2017)","DOI":"10.1109\/ICACCI.2017.8125820"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Gueye, M., Attabi, Y., Dumas, M.: Row conditional-TGAN for generating synthetic relational databases. In: Proceedings of the ICASSP, pp. 1\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10096001"},{"key":"11_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"878","DOI":"10.1007\/11538059_91","volume-title":"Advances in Intelligent Computing","author":"H Han","year":"2005","unstructured":"Han, H., Wang, W.-Y., Mao, B.-H.: Borderline-SMOTE: a new over-sampling method in imbalanced data sets learning. In: Huang, D.-S., Zhang, X.-P., Huang, G.-B. (eds.) ICIC 2005. LNCS, vol. 3644, pp. 878\u2013887. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/11538059_91"},{"key":"11_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ijid.2019.11.009","volume":"91","author":"H Hashimoto","year":"2020","unstructured":"Hashimoto, H., et al.: Indications and classes of outpatient antibiotic prescriptions in Japan: a descriptive study using the national database of electronic health insurance claims, 2012\u20132015. Int. J. Infect. Dis. 91, 1\u20138 (2020)","journal-title":"Int. J. Infect. Dis."},{"key":"11_CR10","unstructured":"Hitachi Ltd.: Manuals - Middleware - Hitachi Advanced Database (2011). https:\/\/itpfdoc.hitachi.co.jp\/Pages\/region\/document_list\/manuals\/en\/hadb.html"},{"issue":"5","key":"11_CR11","doi-asserted-by":"publisher","first-page":"429","DOI":"10.3233\/IDA-2002-6504","volume":"6","author":"N Japkowicz","year":"2002","unstructured":"Japkowicz, N., Stephen, S.: The class imbalance problem: a systematic study. Intell. Data Anal. 6(5), 429\u2013449 (2002)","journal-title":"Intell. Data Anal."},{"key":"11_CR12","first-page":"31504","volume":"37","author":"J Kim","year":"2024","unstructured":"Kim, J., Kim, T., Choo, J.: EPIC: effective prompting for imbalanced-class data synthesis in tabular data classification via large language models. Adv. Neural. Inf. Process. Syst. 37, 31504\u201331542 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR13","unstructured":"Kotelnikov, A., Baranchuk, D., Rubachev, I., Babenko, A.: TabDDPM: modelling tabular data with diffusion models. In: Proceedings of the ICML, pp. 17564\u201317579 (2023)"},{"issue":"2","key":"11_CR14","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1016\/S0016-0032(96)00063-4","volume":"334","author":"ML Men\u00e9ndez","year":"1997","unstructured":"Men\u00e9ndez, M.L., Pardo, J.A., Pardo, L., Pardo, M.D.C.: The Jensen-Shannon divergence. J. Frankl. Inst. 334(2), 307\u2013318 (1997)","journal-title":"J. Frankl. Inst."},{"key":"11_CR15","unstructured":"Ministry of Health, Labour and Welfare: NDB Open Data (2025). https:\/\/www.mhlw.go.jp\/stf\/seisakunitsuite\/bunya\/0000177182.html"},{"issue":"1","key":"11_CR16","doi-asserted-by":"publisher","first-page":"18","DOI":"10.3390\/asi4010018","volume":"4","author":"M Mukherjee","year":"2021","unstructured":"Mukherjee, M., Khushi, M.: SMOTE-ENC: a novel SMOTE-based method to generate synthetic data for nominal and continuous features. Appl. Syst. Innov. 4(1), 18 (2021)","journal-title":"Appl. Syst. Innov."},{"key":"11_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1007\/978-3-642-10424-4_17","volume-title":"Performance Evaluation and Benchmarking","author":"P O\u2019Neil","year":"2009","unstructured":"O\u2019Neil, P., O\u2019Neil, E., Chen, X., Revilak, S.: The star schema benchmark and augmented fact table indexing. In: Nambiar, R., Poess, M. (eds.) TPCTC 2009. LNCS, vol. 5895, pp. 237\u2013252. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-10424-4_17"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Park, N., Mohammadi, M., Gorde, K., Jajodia, S., Park, H., Kim, Y.: Data synthesis based on generative adversarial networks. arXiv preprint arXiv:1806.03384 (2018)","DOI":"10.14778\/3231751.3231757"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Sato, J., Mitsutake, N., Yamada, H., Kitsuregawa, M., Goda, K.: Virtual patient identifier (vPID): improving patient traceability using anonymized identifiers in Japanese healthcare insurance claims database. Heliyon 9(5) (2023)","DOI":"10.1016\/j.heliyon.2023.e16209"},{"key":"11_CR20","unstructured":"SDV Dev Team: CTGAN GitHub repository (2019). https:\/\/github.com\/sdv-dev\/CTGAN"},{"key":"11_CR21","unstructured":"Shi, J., Xu, M., Hua, H., Zhang, H., Ermon, S., Leskovec, J.: TabDiff: a multi-modal diffusion model for tabular data generation. arXiv preprint arXiv:2410.20626 (2024)"},{"key":"11_CR22","unstructured":"Shi, R., Wang, Y., Du, M., Shen, X., Wang, X.: A comprehensive survey of synthetic tabular data generation. arXiv preprint arXiv:2504.16506 (2025)"},{"issue":"3","key":"11_CR23","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1093\/jamia\/ocx079","volume":"25","author":"J Walonoski","year":"2018","unstructured":"Walonoski, J., et al.: Synthea: an approach, method, and software mechanism for generating synthetic patients and the synthetic electronic health care record. J. Am. Med. Inform. Assoc. 25(3), 230\u2013238 (2018)","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"11_CR24","doi-asserted-by":"publisher","first-page":"110895","DOI":"10.1016\/j.asoc.2023.110895","volume":"148","author":"AX Wang","year":"2023","unstructured":"Wang, A.X., Chukova, S.S., Nguyen, B.P.: Synthetic minority oversampling using edited displacement-based k-nearest neighbors. Appl. Soft Comput. 148, 110895 (2023)","journal-title":"Appl. Soft Comput."},{"key":"11_CR25","unstructured":"Xu, L., Skoularidou, M., Cuesta-Infante, A., Veeramachaneni, K.: Modeling tabular data using conditional GAN. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"11_CR26","doi-asserted-by":"publisher","first-page":"1296508","DOI":"10.3389\/fdata.2023.1296508","volume":"6","author":"Z Zhao","year":"2024","unstructured":"Zhao, Z., Kunar, A., Birke, R., Van der Scheer, H., Chen, L.Y.: CTAB-GAN+: enhancing tabular data synthesis. Front. Big Data 6, 1296508 (2024)","journal-title":"Front. Big Data"}],"container-title":["Lecture Notes in Computer Science","Performance Evaluation and Benchmarking"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-18070-4_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T22:22:09Z","timestamp":1777587729000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-18070-4_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032180698","9783032180704"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-18070-4_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TPCTC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Technology Conference on Performance Evaluation and Benchmarking","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"London","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tpctc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.tpc.org\/tpctc\/tpctc2025\/default5.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}