{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T21:57:10Z","timestamp":1781647030695,"version":"3.54.5"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T00:00:00Z","timestamp":1775174400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T00:00:00Z","timestamp":1775174400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Process Sci"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Continual learning, known also as lifelong learning, aims to design learning models that can continuously and autonomously adapt to varying data concepts without forgetting previously collected knowledge. Predictive business process monitoring, which predicts future process steps, is crucial in dynamic environments where tasks are not previously specified and processes frequently change or face unpredictability. However, many existing frameworks assume a static setting, ignoring the dynamic nature and concept drifts in processes, leading to catastrophic forgetting, where training over new data adversely affects the performance on previously learned tasks. This paper presents TFCLPM, a framework for online next activity prediction that operates without relying on predefined tasks and employs continual learning techniques to reduce catastrophic forgetting. The methodology combines a Single Dense Layer neural network with a continual learning algorithm to retain challenging historical samples and stabilize model parameters. Additionally, our approach introduces a diversity-aware memory updating strategy, ensuring that retained samples remain representative of the overall data distribution, leading to more stable adaptation and improved long-term retention. The proposed framework\u2019s performance is compared against six existing online next activity prediction methodologies on synthetic and real-world event logs. Results show significant improvements in prediction accuracy, highlighting the framework\u2019s robustness and efficiency, even on larger datasets with multiple classes.<\/jats:p>","DOI":"10.1007\/s44311-026-00039-7","type":"journal-article","created":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T11:29:00Z","timestamp":1775215740000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Task-free diversity-aware continual learning for online next activity prediction"],"prefix":"10.1007","volume":"3","author":[{"given":"Sjoerd","family":"van Straten","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruozhu","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marwan","family":"Hassani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,3]]},"reference":[{"key":"39_CR1","doi-asserted-by":"crossref","unstructured":"Aljundi R, Babiloni F, Elhoseiny M, Rohrbach M, Tuytelaars T (2018) Memory aware synapses: learning what (not) to forget. ECCV 139\u2013154","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"39_CR2","unstructured":"Aljundi R, Caccia L (2019) Online continual learning with maximally interfered retrieval. NeurIPS 11872\u201311883"},{"key":"39_CR3","doi-asserted-by":"crossref","unstructured":"Aljundi R, Kelchtermans K, Tuytelaars T (2019) Task-free continual learning. In, CVPR, pp 11254\u201311263","DOI":"10.1109\/CVPR.2019.01151"},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"Bang J, Koh H, Park S et al (2022) Online continual learning on a contaminated data stream with blurry task boundaries. In, CVPR, pp 9275\u20139284","DOI":"10.1109\/CVPR52688.2022.00906"},{"issue":"13","key":"39_CR5","doi-asserted-by":"publisher","first-page":"2560","DOI":"10.3390\/electronics13132560","volume":"13","author":"K Cheng","year":"2024","unstructured":"Cheng K, Ma Y, Wang G, Zong L, Liu X (2024) Nlocl: noise-labeled online continual learning. Electronics 13(13):2560","journal-title":"Electronics"},{"key":"39_CR6","unstructured":"Chrysakis A, Moens M-F (2020) Online continual learning from imbalanced data. In: ICML. PMLR, pp 1952\u20131961"},{"key":"39_CR7","first-page":"93","volume":"53","author":"S Ferilli","year":"2019","unstructured":"Ferilli S, Angelastro S (2019) Activity prediction in process mining using the WoMan framework. JIIS 53:93\u2013112","journal-title":"JIIS"},{"key":"39_CR8","doi-asserted-by":"crossref","unstructured":"Gao Z, Cen J, Chang X (2024) Consistent prompting for rehearsal-free continual learning. In, CVPR, pp 28463\u201328473","DOI":"10.1109\/CVPR52733.2024.02689"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Hassani M, Habets S (2021) Predicting next touch point in a customer journey: a use case in telecommunication. ECMS 48\u201354","DOI":"10.7148\/2021-0048"},{"key":"39_CR37","doi-asserted-by":"publisher","unstructured":"Hassani M, Verbeek T, van Straten S (2026) Chameleons do not forget: prompt-based online continual learning for next activity prediction. Int J Coop Inf Syst. https:\/\/doi.org\/10.1142\/S0218843026500036","DOI":"10.1142\/S0218843026500036"},{"key":"39_CR10","doi-asserted-by":"crossref","unstructured":"Huete J, Qahtan AA, Hassani M (2023) PrefixCDD: effective online concept drift detection over event streams using prefix trees. In, COMPSAC, pp 328\u2013333","DOI":"10.1109\/COMPSAC57700.2023.00051"},{"key":"39_CR11","unstructured":"Kirkpatrick J, Pascanu R, Rabinowitz N et al (2016) Overcoming catastrophic forgetting in neural networks. CoRR Abs\/1612.00796"},{"key":"39_CR12","doi-asserted-by":"crossref","unstructured":"Kosciuszek T, Hassani M (2024) Online next activity prediction under concept drifts. CAiSE Workshops 335\u2013346","DOI":"10.1007\/978-3-031-61003-5_28"},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"Lesort T, Caselles-Dupr\u00e9 H, Garcia-Ortiz M et al (2019) Generative models from the perspective of continual learning. IJCNN 1\u20138","DOI":"10.1109\/IJCNN.2019.8851986"},{"issue":"12","key":"39_CR14","doi-asserted-by":"publisher","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","volume":"40","author":"Z Li","year":"2017","unstructured":"Li Z, Hoiem D (2017) Learning without forgetting. IEEE T Pattern Anal 40(12):2935\u20132947","journal-title":"IEEE T Pattern Anal"},{"key":"39_CR15","first-page":"6470","volume":"30","author":"D Lopez-Paz","year":"2017","unstructured":"Lopez-Paz D, Ranzato M (2017) Gradient episodic memory for continual learning. Adv Neural Inf Process Syst 30:6470\u20136479","journal-title":"Adv Neural Inf Process Syst"},{"key":"39_CR16","doi-asserted-by":"crossref","unstructured":"Maaradji A, Dumas M, La Rosa M, Ostovar A (2015) Fast and accurate business process drift detection. BPM 406\u2013422","DOI":"10.1007\/978-3-319-23063-4_27"},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Maisenbacher M, Weidlich M (2017) Handling concept drift in predictive process monitoring. In, SCC. IEEE, pp 1\u20138","DOI":"10.1109\/SCC.2017.10"},{"key":"39_CR18","doi-asserted-by":"crossref","unstructured":"Pauwels S, Calders T (2021) Incremental predictive process monitoring: the next activity case. In, BPM, pp 123\u2013140","DOI":"10.1007\/978-3-030-85469-0_10"},{"key":"39_CR19","unstructured":"Rahman MS, Coull S, Yu Q, Wright M (2025) Madar: efficient continual learning for malware analysis with diversity-aware replay. https:\/\/doi.org\/arXiv:2502.05760"},{"key":"39_CR20","volume-title":"Progressive prompts: continual learning for language models","author":"A Razdaibiedina","year":"2023","unstructured":"Razdaibiedina A, Mao Y, Hou R et al (2023) Progressive prompts: continual learning for language models. https:\/\/doi.org\/arXiv:2301.12314"},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"Rebuffi S, Kolesnikov A, Sperl G, Lampert CH (2017) iCarl: incremental classifier and representation learning. In, CVPR, pp 5533\u20135542","DOI":"10.1109\/CVPR.2017.587"},{"issue":"5","key":"39_CR22","doi-asserted-by":"publisher","first-page":"1385","DOI":"10.1007\/s10115-022-01666-9","volume":"64","author":"W Rizzi","year":"2022","unstructured":"Rizzi W, Di Francescomarino C, Ghidini C, Maggi FM (2022) How do i update my model? On the resilience of predictive process monitoring models to change. Knowl Inf Syst 64(5):1385\u20131416","journal-title":"Knowl Inf Syst"},{"key":"39_CR23","unstructured":"Rolnick D, Ahuja A, Schwarz J et al (2019) Experience replay for continual learning. Adv Neural Inf Process Syst"},{"key":"39_CR24","doi-asserted-by":"crossref","unstructured":"Rubner Y, Tomasi C, Guibas L.J. (1998) A metric for distributions with applications to image databases. In ICCV:59\u201366","DOI":"10.1109\/ICCV.1998.710701"},{"key":"39_CR25","unstructured":"Rusu AA, Rabinowitz NC, Desjardins G et al (2016) Progressive neural networks. CoRR Abs\/1606.04671"},{"key":"39_CR26","doi-asserted-by":"crossref","unstructured":"Taymouri F, La Rosa M, Erfani S.M. (2021) A deep adversarial model for suffix and remaining time prediction of event sequences. In, SDM, pp 522\u2013530","DOI":"10.1137\/1.9781611976700.59"},{"key":"39_CR28","doi-asserted-by":"crossref","unstructured":"Verbeek T, Hassani M (2024) Handling catastrophic forgetting: online continual learning for next activity prediction. CoopIS 225\u2013242","DOI":"10.1007\/978-3-031-81375-7_13"},{"key":"39_CR29","doi-asserted-by":"crossref","unstructured":"Verbeek T, Yao R, Hassani M (2025) Task-free continual learning with dynamic loss for online next activity prediction. In ICPM Workshops, pp 693\u2013705","DOI":"10.1007\/978-3-031-82225-4_51"},{"key":"39_CR30","doi-asserted-by":"crossref","unstructured":"Wang Z, Zhang Z, Ebrahimi S et al (2022) DualPrompt: complementary prompting for rehearsal-free continual learning. ECCV 631\u2013648","DOI":"10.1007\/978-3-031-19809-0_36"},{"key":"39_CR31","doi-asserted-by":"crossref","unstructured":"Wang Z, Zhang Z, Lee C-Y et al (2022) Learning to prompt for continual learning. In, CVPR, pp 139\u2013149","DOI":"10.1109\/CVPR52688.2022.00024"},{"issue":"1","key":"39_CR32","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1023\/A:1018046501280","volume":"23","author":"G Widmer","year":"1996","unstructured":"Widmer G, Kubat M (1996) Learning in the presence of concept drift and hidden contexts. Mach Learn 23(1):69\u2013101","journal-title":"Mach Learn"},{"key":"39_CR33","doi-asserted-by":"crossref","unstructured":"Wolters L, Hassani M (2022) Predicting activities of interest in the remainder of customer journeys under online settings. ICPM 145\u2013157","DOI":"10.1007\/978-3-031-27815-0_11"},{"key":"39_CR34","doi-asserted-by":"publisher","first-page":"102228","DOI":"10.1016\/j.is.2023.102228","volume":"117","author":"R Zaman","year":"2023","unstructured":"Zaman R, Hassani M, Dongen BF (2023) Conformance checking of process event streams with constraints on data retention. Inf Syst 117:102228","journal-title":"Inf Syst"}],"container-title":["Process Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44311-026-00039-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44311-026-00039-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44311-026-00039-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T21:27:49Z","timestamp":1781645269000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44311-026-00039-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,3]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["39"],"URL":"https:\/\/doi.org\/10.1007\/s44311-026-00039-7","relation":{},"ISSN":["2948-2178"],"issn-type":[{"value":"2948-2178","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,3]]},"assertion":[{"value":"31 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"7"}}