{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T08:08:01Z","timestamp":1779178081455,"version":"3.51.4"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T00:00:00Z","timestamp":1779148800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T00:00:00Z","timestamp":1779148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100005713","name":"Technische Universit\u00e4t M\u00fcnchen","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005713","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Process Sci"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Predictive Process Monitoring (PPM) aims to forecast the future behavior of an ongoing process instance based on historical event logs. PPM approaches which follow an offline training and online prediction paradigm, often struggle to adapt to the evolving nature of real-world processes. While state-of-the-art approaches address such challenges by continuously updating or retraining models, they typically overlook dynamic processes, where numerous unseen activities emerge or the order between activities evolves over time. To address this gap, we propose the Drift-Adaptive Class Incremental Learning (DA-CIL) framework for next activity prediction in dynamic process environments. DA-CIL employs a representation-based drift detection mechanism to identify shifted or unseen activities. To enhance model generalization to drifting patterns, DA-CIL applies data augmentation in feature space to generate diverse and novel feature representations that are unseen but likely to occur as processes evolve. Upon drift detection, the model is incrementally updated to the newly observed data in combination with augmented samples and knowledge distillation. Experiments on real-life event logs demonstrate that DA-CIL consistently outperforms existing methods in prediction accuracy and adaptation efficiency, highlighting its effectiveness for next activity prediction in highly dynamic process environments.<\/jats:p>","DOI":"10.1007\/s44311-026-00048-6","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T07:28:58Z","timestamp":1779175738000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DA-CIL: Drift-Adaptive Class Incremental Learning for dynamic processes"],"prefix":"10.1007","volume":"3","author":[{"given":"Qian","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefanie","family":"Rinderle-Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,19]]},"reference":[{"issue":"1","key":"48_CR1","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1109\/TNNLS.2013.2278313","volume":"25","author":"RPJC Bose","year":"2014","unstructured":"Bose RPJC, Aalst WMP, Zliobaite I, Pechenizkiy M (2014) Dealing with concept drifts in process mining. IEEE Trans Neural Netw Learn Syst 25(1):154\u2013171. https:\/\/doi.org\/10.1109\/TNNLS.2013.2278313","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"48_CR2","unstructured":"Bukhsh ZA, Saeed A, Dijkman RM (2021) Processtransformer: predictive business process monitoring with transformer network. CoRr abs\/2104.00721 2104.00721"},{"key":"48_CR3","doi-asserted-by":"publisher","unstructured":"Camargo M, Dumas M, Rojas OG (2019) Learning accurate LSTM models of business processes. In: Business process management. pp 286\u2013302. https:\/\/doi.org\/10.1007\/978-3-030-26619-6_19","DOI":"10.1007\/978-3-030-26619-6_19"},{"issue":"3","key":"48_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1541880.1541882","volume":"41","author":"V Chandola","year":"2009","unstructured":"Chandola V, Banerjee A, Kumar V (2009) Anomaly detection: a survey. ACM Comput Surv 41(3):1\u201358. https:\/\/doi.org\/10.1145\/1541880.1541882","journal-title":"ACM Comput Surv"},{"key":"48_CR5","doi-asserted-by":"publisher","unstructured":"Chen Q, Rinderle-Ma S (2025) Class incremental learning with drift detection and data augmentation for dynamic processes. In: International Conference on Process Mining. pp 1\u20138. https:\/\/doi.org\/10.1109\/ICPM66919.2025.11220682","DOI":"10.1109\/ICPM66919.2025.11220682"},{"key":"48_CR6","doi-asserted-by":"publisher","unstructured":"Chen Q, Winter K, Rinderle-Ma S (2023) Predicting unseen process behavior based on context information from compliance constraints. In: Business process management forum. pp 127\u2013144. https:\/\/doi.org\/10.1007\/978-3-031-41623-1_8","DOI":"10.1007\/978-3-031-41623-1_8"},{"key":"48_CR7","doi-asserted-by":"publisher","unstructured":"Chen Q, Winter K, Rinderle-Ma S (2025) Predicting unseen process behavior based on log injection. In: International Conference on Business Process Modeling, Development and Support. Lecture Notes in Business Information Processing, vol 558. pp 159\u2013175. https:\/\/doi.org\/10.1007\/978-3-031-95397-2_10","DOI":"10.1007\/978-3-031-95397-2_10"},{"key":"48_CR8","doi-asserted-by":"publisher","unstructured":"Deng Y, Wang J, Wang C, Zheng C, Li M, Li B (2024) Enhancing predictive process monitoring with sequential graphs and trace attention. In: Web services. pp 406\u2013415. https:\/\/doi.org\/10.1109\/ICWS62655.2024.00062","DOI":"10.1109\/ICWS62655.2024.00062"},{"key":"48_CR9","doi-asserted-by":"publisher","unstructured":"Dongen BF, Crooy RA, Aalst WMP (2008) Cycle time prediction: when will this case finally be finished? In: On the move to meaningful internet systems. Lect Notes Comput Sci 5331:319\u2013336. https:\/\/doi.org\/10.1007\/978-3-540-88871-0_22","DOI":"10.1007\/978-3-540-88871-0_22"},{"key":"48_CR10","doi-asserted-by":"publisher","unstructured":"Elyasi KA, Aa H, Stuckenschmidt H (2024) Pgtnet: a process graph transformer network for remaining time prediction of business process instances. In: Advanced information systems engineering. pp 124\u2013140. https:\/\/doi.org\/10.1007\/978-3-031-61057-8_8","DOI":"10.1007\/978-3-031-61057-8_8"},{"key":"48_CR11","doi-asserted-by":"publisher","unstructured":"Evermann J, Rehse J, Fettke P (2016) A deep learning approach for predicting process behaviour at runtime. In: Business process management workshops. pp 327\u2013338. https:\/\/doi.org\/10.1007\/978-3-319-58457-7_24","DOI":"10.1007\/978-3-319-58457-7_24"},{"key":"48_CR12","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/J.DSS.2017.04.003","volume":"100","author":"J Evermann","year":"2017","unstructured":"Evermann J, Rehse J, Fettke P (2017) Predicting process behaviour using deep learning. Decis Support Syst 100:129\u2013140. https:\/\/doi.org\/10.1016\/J.DSS.2017.04.003","journal-title":"Decis Support Syst"},{"issue":"6","key":"48_CR13","doi-asserted-by":"publisher","first-page":"896","DOI":"10.1109\/TSC.2016.2645153","volume":"12","author":"CD Francescomarino","year":"2019","unstructured":"Francescomarino CD, Dumas M, Maggi FM, Teinemaa I (2019) Clustering-based predictive process monitoring. IEEE Trans Serv Comput 12(6):896\u2013909. https:\/\/doi.org\/10.1109\/TSC.2016.2645153","journal-title":"IEEE Trans Serv Comput"},{"key":"48_CR14","doi-asserted-by":"publisher","unstructured":"Kosciuszek T, Hassani M (2024) Online next activity prediction under concept drifts. In: Advanced Information Systems Engineering Workshops, pp 335\u2013346. https:\/\/doi.org\/10.1007\/978-3-031-61003-5_28","DOI":"10.1007\/978-3-031-61003-5_28"},{"issue":"1","key":"48_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s44311-025-00012-w","volume":"2","author":"A Kraus","year":"2025","unstructured":"Kraus A, Aa H (2025) Machine learning-based detection of concept drift in business processes. Process Sci 2(1):1\u201326. https:\/\/doi.org\/10.1007\/s44311-025-00012-w","journal-title":"Process Sci"},{"issue":"4","key":"48_CR16","doi-asserted-by":"publisher","first-page":"764","DOI":"10.1016\/j.jesp.2013.03.013","volume":"49","author":"C Leys","year":"2013","unstructured":"Leys C, Ley C, Klein O, Bernard P, Licata L (2013) Detecting outliers: do not use standard deviation around the mean, use absolute deviation around the median. J Educ Chang Exp Soc Phychol 49(4):764\u2013766. https:\/\/doi.org\/10.1016\/j.jesp.2013.03.013","journal-title":"J Educ Chang Exp Soc Phychol"},{"key":"48_CR17","doi-asserted-by":"publisher","unstructured":"Mangat AS, Rinderle-Ma S (2022) Next-activity prediction for non-stationary processes with unseen data variability. In: Enterprise design, operations, and computing. pp 145\u2013161. https:\/\/doi.org\/10.1007\/978-3-031-17604-3_9","DOI":"10.1007\/978-3-031-17604-3_9"},{"key":"48_CR18","doi-asserted-by":"publisher","unstructured":"Mauro ND, Appice A, Basile TMA (2019) Activity prediction of business process instances with inception NN models. In: AI*IA 2019 - advances in artificial intelligence. pp 348\u2013361. https:\/\/doi.org\/10.1007\/978-3-030-35166-3_25","DOI":"10.1007\/978-3-030-35166-3_25"},{"key":"48_CR19","doi-asserted-by":"publisher","unstructured":"Navarin N, Vincenzi B, Polato M, Sperduti A (2017) LSTM networks for data-aware remaining time prediction of business process instances. In Symposium Series on Computational Intelligence, pp 1\u20137. https:\/\/doi.org\/10.1109\/SSCI.2017.8285184","DOI":"10.1109\/SSCI.2017.8285184"},{"key":"48_CR20","doi-asserted-by":"publisher","unstructured":"Pauwels S, Calders T (2021) Incremental predictive process monitoring: the next activity case. Bus Process Manag 123\u2013140. https:\/\/doi.org\/10.1007\/978-3-030-85469-0_10","DOI":"10.1007\/978-3-030-85469-0_10"},{"key":"48_CR21","unstructured":"Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. Adv Neural Inf Process Syst 30"},{"key":"48_CR22","doi-asserted-by":"publisher","unstructured":"Tax N, Verenich I, Rosa ML, Dumas M (2017) Predictive business process monitoring with LSTM neural networks. In: Advanced information systems engineering (CAiSE 2017). pp 477\u2013492. https:\/\/doi.org\/10.1007\/978-3-319-59536-8_30","DOI":"10.1007\/978-3-319-59536-8_30"},{"key":"48_CR23","doi-asserted-by":"publisher","unstructured":"Taymouri F, Rosa ML, Erfani SM, Bozorgi ZD, Verenich I (2020) Predictive business process monitoring via generative adversarial nets: the case of next event prediction. In: Business process management. pp 237\u2013256. https:\/\/doi.org\/10.1007\/978-3-030-58666-9_14","DOI":"10.1007\/978-3-030-58666-9_14"},{"key":"48_CR24","doi-asserted-by":"publisher","unstructured":"Teinemaa I, Dumas M, Maggi FM, Francescomarino CD (2016) Predictive business process monitoring with structured and unstructured data. In: Business process management. pp 401\u2013417. https:\/\/doi.org\/10.1007\/978-3-319-45348-4_23","DOI":"10.1007\/978-3-319-45348-4_23"},{"issue":"2","key":"48_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3301300","volume":"13","author":"I Teinemaa","year":"2019","unstructured":"Teinemaa I, Dumas M, Rosa ML, Maggi FM (2019) Outcome-oriented predictive process monitoring: review and benchmark. ACM Trans Knowl Discov Data 13(2):1\u201357. https:\/\/doi.org\/10.1145\/3301300","journal-title":"ACM Trans Knowl Discov Data"},{"key":"48_CR26","doi-asserted-by":"publisher","unstructured":"Verbeek T, Hassani M (2024) Handling catastrophic forgetting: online continual learning for next activity prediction. Cooperative Inf Syst 225\u2013242. https:\/\/doi.org\/10.1007\/978-3-031-81375-7_13","DOI":"10.1007\/978-3-031-81375-7_13"},{"key":"48_CR27","doi-asserted-by":"publisher","unstructured":"Verbeek T, Yao R, Hassani M (2024) Task-free continual learning with dynamic loss for online next activity prediction. In: Process mining workshops. Lect Notes Bus Info Proces 533:693\u2013705. https:\/\/doi.org\/10.1007\/978-3-031-82225-4_51","DOI":"10.1007\/978-3-031-82225-4_51"},{"key":"48_CR28","unstructured":"Weinzierl S, Zilker S, Brunk J, Revoredo K, Nguyen A, Matzner M, Becker J, Eskofier BM (2020) An empirical comparison of deep-neural-network architectures for next activity prediction using context-enriched process event logs. CoRr abs\/2005.01194 2005.01194"},{"key":"48_CR29","doi-asserted-by":"publisher","unstructured":"Zheng C, Wen L, Wang J (2017) Detecting process concept drifts from event logs. In: On the move to meaningful internet systems. pp 524\u2013542. https:\/\/doi.org\/10.1007\/978-3-319-69462-7_33","DOI":"10.1007\/978-3-319-69462-7_33"},{"key":"48_CR30","unstructured":"Zhu F, Cheng Z, Zhang X, Liu C (2021) Class-incremental learning via dual augmentation. Adv Neural Inf Process Syst, pp 14306\u201314318. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/77ee3bc58ce560b86c2b59363281e914-Abstract.html"}],"container-title":["Process Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44311-026-00048-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44311-026-00048-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44311-026-00048-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T07:29:04Z","timestamp":1779175744000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44311-026-00048-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,19]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["48"],"URL":"https:\/\/doi.org\/10.1007\/s44311-026-00048-6","relation":{},"ISSN":["2948-2178"],"issn-type":[{"value":"2948-2178","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,19]]},"assertion":[{"value":"15 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 May 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":"Ethics approval and consent to participate"}},{"value":"The authors declare no competing interests..","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"10"}}