{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T05:52:52Z","timestamp":1777441972642,"version":"3.51.4"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031822247","type":"print"},{"value":"9783031822254","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T00:00:00Z","timestamp":1743120000000},"content-version":"vor","delay-in-days":86,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Process mining allows the discovery of business processes from an event log. However, event logs are rapidly increasing in size and process mining algorithms struggle with the computational load when efficient processing is required. This calls for methods that decrease the event log size while still preserving the representativeness of the event log. This paper presents two new algorithms for sampling event logs. The first algorithm called  chooses traces from an event log above a threshold and subsequently selects traces with underrepresented Directly Follows Relations. The second sampling algorithm called  selects samples that have a high intersection of Directly Follows Relations with the original event log. Usually,  is complemented with  for a more accurate sample representation. They perform well for conformance checking and excel in certain scenarios for process discovery. Thus, both algorithms outperform existing sampling algorithms.<\/jats:p>","DOI":"10.1007\/978-3-031-82225-4_4","type":"book-chapter","created":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T02:59:25Z","timestamp":1743303565000},"page":"44-56","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Representative Sampling in\u00a0Process Mining: Two Novel Sampling Algorithms for\u00a0Event Logs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8445-8104","authenticated-orcid":false,"given":"Frederik","family":"Fonger","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1945-9051","authenticated-orcid":false,"given":"Niclas","family":"Nebelung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8105-382X","authenticated-orcid":false,"given":"Arvid","family":"Lepsien","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0472-1262","authenticated-orcid":false,"given":"Milda","family":"Aleknonyt\u0117-Resch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8206-7636","authenticated-orcid":false,"given":"Agnes","family":"Koschmider","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,28]]},"reference":[{"key":"4_CR1","series-title":"Lecture Notes in Business Information Processing","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/978-3-642-28108-2_19","volume-title":"Business Process Management Workshops","author":"W van der Aalst","year":"2012","unstructured":"van der Aalst, W., et al.: Process mining manifesto. In: Daniel, F., Barkaoui, K., Dustdar, S. (eds.) BPM 2011. LNBIP, vol. 99, pp. 169\u2013194. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-28108-2_19"},{"key":"4_CR2","doi-asserted-by":"publisher","unstructured":"van\u00a0der Aalst, W.M.: Foundations of process discovery. In: Process Mining Handbook, pp. 37\u201375. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-08848-3_2","DOI":"10.1007\/978-3-031-08848-3_2"},{"key":"4_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2020.101666","volume":"104","author":"M Bauer","year":"2022","unstructured":"Bauer, M., van der Aa, H., Weidlich, M.: Sampling and approximation techniques for efficient process conformance checking. Inf. Syst. 104, 101666 (2022)","journal-title":"Inf. Syst."},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Bernard, G., Andritsos, P.: Selecting representative sample traces from large event logs. In: ICPM 2021, pp. 56\u201363. IEEE, Eindhoven, Netherlands (2021)","DOI":"10.1109\/ICPM53251.2021.9576679"},{"key":"4_CR5","doi-asserted-by":"publisher","unstructured":"Carmona, J., van Dongen, B., Weidlich, M.: Conformance checking: foundations, milestones and challenges. In: Process Mining Handbook, pp. 155\u2013190. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-08848-3_5","DOI":"10.1007\/978-3-031-08848-3_5"},{"key":"4_CR6","unstructured":"van Dongen, B.: Bpi challenge 2012 (2012). https:\/\/data.4tu.nl\/articles\/dataset\/BPI_Challenge_2012\/12689204"},{"key":"4_CR7","unstructured":"van Dongen, B.: Bpi challenge 2020 (2020). https:\/\/data.4tu.nl\/collections\/_\/5065541\/1"},{"key":"4_CR8","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/978-3-030-30278-8_39","volume-title":"New Trends in Databases and Information Systems","author":"M Fani Sani","year":"2019","unstructured":"Fani Sani, M., van Zelst, S.J., van\u00a0der Aalst, W.M.P.: The impact of event log subset selection on the performance of process discovery algorithms. In: Welzer, T., et al. (eds.) ADBIS 2019. CCIS, vol. 1064, pp. 391\u2013404. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-30278-8_39"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Fani\u00a0Sani, M., van Zelst, S.J., van\u00a0der Aalst, W.M.P.: The impact of biased sampling of event logs on the performance of process discovery. Computing 103(6), 1085\u20131104 (2021)","DOI":"10.1007\/s00607-021-00910-4"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Fani\u00a0Sani, M., et\u00a0al.: Event log sampling for predictive monitoring. In: International Conference on Process Mining, vol.\u00a0433, pp. 154\u2013166 (2022)","DOI":"10.1007\/978-3-030-98581-3_12"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Kabierski, M., et\u00a0al.: Sampling what matters: Relevance-guided sampling of event logs. In: ICPM 2021. pp. 64\u201371 (2021)","DOI":"10.1109\/ICPM53251.2021.9576875"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Knols, B., van\u00a0der Werf, J.M.E.M.: Measuring the behavioral quality of log sampling. In: ICPM 2019, pp. 97\u2013104. IEEE, Aachen (2019)","DOI":"10.1109\/ICPM.2019.00024"},{"key":"4_CR13","unstructured":"Koschmider, A., et\u00a0al.: Process mining for unstructured data: challenges and research directions. In: Modellierung 2024, pp. 119\u2013136. GI, Bonn (2024)"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Liu, C., et\u00a0al.: Sampling business process event logs using graph-based ranking model. Concurr. Computat.: Pract. Exper. 33(5), e5974 (2021)","DOI":"10.1002\/cpe.5974"},{"key":"4_CR15","unstructured":"Mannhardt, F., Blinde, D.: Analyzing the trajectories of patients with sepsis using process mining. In: RADAR+EMISA 2017, Essen, Germany, 12\u201313 June 2017, pp. 72\u201380. CEUR Workshop Proceedings, CEUR-WS.org (2017)"},{"issue":"3","key":"4_CR16","doi-asserted-by":"publisher","first-page":"927","DOI":"10.2298\/CSIS200127028S","volume":"17","author":"M Sani","year":"2020","unstructured":"Sani, M., Van Zelst, S., Van Der Aalst, W.: Improving the performance of process discovery algorithms by instance selection. Comp. Sci. Inf. Syst. 17(3), 927\u2013958 (2020)","journal-title":"Comp. Sci. Inf. Syst."},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Van Der\u00a0Aalst, W.: Process Mining. Springer, Heidelberg (2016)","DOI":"10.1007\/978-3-662-49851-4"},{"key":"4_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2022.102155","volume":"114","author":"JMEM van der Werf","year":"2023","unstructured":"van der Werf, J.M.E.M., et al.: All that glitters is not gold: four maturity stages of process discovery algorithms. Inf. Syst. 114, 102155 (2023)","journal-title":"Inf. Syst."}],"container-title":["Lecture Notes in Business Information Processing","Process Mining Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-82225-4_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T16:05:41Z","timestamp":1760889941000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-82225-4_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031822247","9783031822254"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-82225-4_4","relation":{},"ISSN":["1865-1348","1865-1356"],"issn-type":[{"value":"1865-1348","type":"print"},{"value":"1865-1356","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"28 March 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Process Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lyngby","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Denmark","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpm2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpmconference.org\/2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}