{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T10:04:07Z","timestamp":1773569047286,"version":"3.50.1"},"reference-count":35,"publisher":"Association for Computing Machinery (ACM)","issue":"1","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61572035"],"award-info":[{"award-number":["61572035"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003995","name":"Anhui Provincial Natural Science Foundation","doi-asserted-by":"crossref","award":["2308085US11"],"award-info":[{"award-number":["2308085US11"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100017668","name":"Key Research and Development Program of Anhui Province","doi-asserted-by":"crossref","award":["2022a05020005"],"award-info":[{"award-number":["2022a05020005"]}],"id":[{"id":"10.13039\/501100017668","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Leading Backbone Talent Project in Anhui Province","award":["2020-1-12"],"award-info":[{"award-number":["2020-1-12"]}]},{"name":"Anhui Province Academic and Technical Leader Foundation","award":["2022D327"],"award-info":[{"award-number":["2022D327"]}]},{"name":"High-level Talents Introduction Research Start-up Fund Project of Anhui University of Science and Technology","award":["2023yjrc86"],"award-info":[{"award-number":["2023yjrc86"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Manage. Inf. Syst."],"published-print":{"date-parts":[[2026,3,31]]},"abstract":"<jats:p>Anomalies in business processes can lead to significant losses, making timely detection and handling of these anomalies essential for business process management and optimization. Although current methods in business processes might uncover abnormal cases or attributes in logs, they fail to provide adequate explanations for the anomalies detected. To enable reliable detection, a multi-perspective anomaly detection and explanation method for business processes based on graph neural networks is proposed. Firstly, a graph structure is constructed to reveal the dependencies between various attributes. On this basis, a multiple-graph neural network predictor is trained to predict each attribute of the next event separately. Then, according to the probability distribution of the prediction results, the anomaly score is calculated, and the anomalous attributes and cases are identified. In addition, when an anomaly is detected, a relevance score is assigned to the event attributes in the prefix trace. This score explains the rationale for anomaly detection. The experimental results demonstrate the method's efficacy in detecting anomalies in business processes, providing practical explanations, and enhancing the transparency and credibility of the model.<\/jats:p>","DOI":"10.1145\/3779301","type":"journal-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T11:51:38Z","timestamp":1765194698000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Explainable Multi-perspective Business Process Anomaly Detection Method Based on Graph Neural Networks"],"prefix":"10.1145","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3953-2452","authenticated-orcid":false,"given":"Wei","family":"Bao","sequence":"first","affiliation":[{"name":"School of Mathematics and Big Data, Anhui University of Science and Technology","place":["Huainan, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0792-2628","authenticated-orcid":false,"given":"Ke","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Mathematics and Big Data, Anhui University of Science and Technology","place":["Huainan, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8531-7215","authenticated-orcid":false,"given":"Xianwen","family":"Fang","sequence":"additional","affiliation":[{"name":"Anhui Province Engineering Laboratory for Big Data Analysis and Early Warning Technology of Coal Mine Safety, Anhui University of Science and Technology","place":["Huainan, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8013-3898","authenticated-orcid":false,"given":"Xiwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mathematics and Big Data, Anhui University of Science and Technology","place":["Huainan, China"]}]}],"member":"320","published-online":{"date-parts":[[2026,3,10]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","unstructured":"W. van der Aalst T. Weijters and L. Maruster. 2004. Workflow mining: Discovering process models from event logs. IEEE Transactions on Knowledge and Data Engineering 16 9 (2004) 1128\u20131142. DOI:10.1109\/TKDE.2004.47","DOI":"10.1109\/TKDE.2004.47"},{"key":"e_1_3_1_3_2","unstructured":"Tianle Cai Shengjie Luo Keyulu Xu Di He Tie-Yan Liu and Liwei Wang. 2021. GraphNorm: A principled approach to accelerating graph neural network training. In Proceedings of the 38th International Conference on Machine Learning (ICML'21) Virtual Event. PMLR 139 (2021) 1204\u20131215. Retrieved from https:\/\/proceedings.mlr.press\/v139\/cai21e.html"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","unstructured":"Julian Caspary Adrian Rebmann and Han van der Aa. 2023. Does this make sense? Machine learning-based detection of semantic anomalies in business processes. In Proceedings of the 21st International Conference on Business Process Management BPM 2023. Springer-Verlag Berlin 163\u2013179. DOI:10.1007\/978-3-031-41620-0_10","DOI":"10.1007\/978-3-031-41620-0_10"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","unstructured":"Varun Chandola Arindam Banerjee and Vipin Kumar. 2009. Anomaly detection: A survey. ACM Computing Surveys 41 3 Article 15 (2009) 58. DOI:10.1145\/1541880.1541882","DOI":"10.1145\/1541880.1541882"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","unstructured":"Joerg Evermann Jana-Rebecca Rehse and Peter Fettke. 2017. Predicting process behaviour using deep learning. Decision Support Systems 100 (2017) 129\u2013140. DOI:10.1016\/j.dss.2017.04.003","DOI":"10.1016\/j.dss.2017.04.003"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","unstructured":"Riccardo Galanti Bernat Coma-Puig Massimiliano de Leoni Josep Carmona and Nicol\u00f2 Navarin. 2020. Explainable predictive process monitoring. In Proceedings of the 2020 2nd International Conference on Process Mining (ICPM). 1\u20138. DOI:10.1109\/ICPM49681.2020.00012","DOI":"10.1109\/ICPM49681.2020.00012"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","unstructured":"Wei Guan Jian Cao Yang Gu and Shiyou Qian. 2023. GRASPED: A GRU-AE network based multi-perspective business process anomaly detection model. IEEE Transactions on Services Computing 16 5 (2023) 3412\u20133424. DOI:10.1109\/TSC.2023.3262405","DOI":"10.1109\/TSC.2023.3262405"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","unstructured":"Wei Guan Jian Cao Yang Gu and Shiyou Qian. 2024. GAMA: A multi-graph-based anomaly detection framework for business processes via graph neural networks. Information Systems 124 Article 102405 (2024) 15 pages. DOI:10.1016\/j.is.2024.102405","DOI":"10.1016\/j.is.2024.102405"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","unstructured":"Ping-Yu Hsu Yu-Cheng Chuang Yao-Chung Lo and Shuang-Chuan He. 2017. Using contextualized activity-level duration to discover irregular process instances in business operations. Information Sciences 391\u2013392 (2017) 80\u201398. DOI:10.1016\/j.ins.2016.10.027","DOI":"10.1016\/j.ins.2016.10.027"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","unstructured":"Adil Hussein Paolo Falcarin and Ahmed Sadiq. 2021. Enhancement performance of random forest algorithm via one hot encoding for IoT IDS. Periodicals of Engineering and Natural Sciences (PEN) 9 3 (2021) 579\u2013591. DOI:10.21533\/pen.v9i3.2204","DOI":"10.21533\/pen.v9i3.2204"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","unstructured":"Md Ibne Joha Md Minhazur Rahman Md Shahriar Nazim and Yeong Min Jang. 2024. A secure IIoT environment that integrates AI-driven real-time short-term active and reactive load forecasting with anomaly detection: A real-world application. Sensors 24 23 Article 7440 (2024) 33. DOI:10.3390\/s24237440","DOI":"10.3390\/s24237440"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","unstructured":"Jonghyeon Ko and Marco Comuzzi. 2021. Detecting anomalies in business process event logs using statistical leverage. Information Sciences 549 (2021) 53\u201367. DOI:10.1016\/j.ins.2020.11.017","DOI":"10.1016\/j.ins.2020.11.017"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","unstructured":"Fabian K\u00f6nig Andreas Egger Wolfgang Kratsch Maximilian R\u00f6glinger and Niklas W\u00f6rdehoff. 2025. Unstructured data in process mining: A systematic literature review. ACM Transactions on Management Information Systems 16 3 Article 25 (2025) 34 pages. DOI:10.1145\/3727148","DOI":"10.1145\/3727148"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","unstructured":"Philippe Krajsic and Bogdan Franczyk. 2021. Semi-supervised anomaly detection in business process event data using self-attention based classification. Procedia Computer Science 192 (2021) 39\u201348. DOI:10.1016\/j.procs.2021.08.005","DOI":"10.1016\/j.procs.2021.08.005"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","unstructured":"Johannes Lahann Peter Pfeiffer and Peter Fettke. 2023. LSTM-based anomaly detection of process instances: Benchmark and tweaks. In Proceedings of the Process Mining Workshops. Springer Nature Switzerland Cham 229\u2013241. DOI:10.1007\/978-3-031-27815-0_17","DOI":"10.1007\/978-3-031-27815-0_17"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","unstructured":"Suhwan Lee Xixi Lu and Hajo A. Reijers. 2022. The analysis of online event streams: Predicting the next activity for anomaly detection. In Research Challenges in Information Science R. Guizzardi J. Ralyt\u00e9 and X. Franch (Eds.). Springer International Publishing Cham 248\u2013264. DOI:10.1007\/978-3-031-05760-1_15","DOI":"10.1007\/978-3-031-05760-1_15"},{"key":"e_1_3_1_18_2","unstructured":"Yujia Li Richard Zemel Marc Brockschmidt and Daniel Tarlow. 2016. Gated graph sequence neural networks. In Proceedings of the 4th International Conference on Learning Representations (ICLR). Retrieved December 30 2024 from https:\/\/www.microsoft.com\/en-us\/research\/publication\/gated-graph-sequence-neural-networks\/"},{"key":"e_1_3_1_19_2","unstructured":"Scott M. Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS\u201917). Curran Associates Inc. Red Hook NY USA 4768\u20134777."},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","unstructured":"Wanlun Ma Xiangyu Hu Chao Chen Sheng Wen Kkwang Raymond Choo and Yang Xiang. 2022. Social media event prediction using DNN with feedback mechanism. ACM Transactions on Management Information Systems 13 3 Article 33 (2022) 24 pages. DOI:10.1145\/3522759","DOI":"10.1145\/3522759"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","unstructured":"Nijat Mehdiyev and Peter Fettke. 2021. Explainable artificial intelligence for process mining: A general overview and application of a novel local explanation approach for predictive process monitoring. In Interpretable Artificial Intelligence: A Perspective of Granular Computing W. Pedrycz and S.-M. Chen (Eds.). Springer International Publishing Cham 1\u201328. DOI:10.1007\/978-3-030-64949-4_1","DOI":"10.1007\/978-3-030-64949-4_1"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","unstructured":"Azadeh Sadat Mozafari Mehr Renata M. De Carvalho and Boudewijn Van Dongen. 2023. Explainable conformance checking: Understanding patterns of anomalous behavior. Engineering Applications of Artificial Intelligence 126 Article 106827 (2023) 14. DOI:10.1016\/j.engappai.2023.106827","DOI":"10.1016\/j.engappai.2023.106827"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","unstructured":"Timo Nolle Stefan Luettgen Alexander Seeliger and Max M\u00fchlh\u00e4user. 2018. Analyzing business process anomalies using autoencoders. Machine Learning 107 11 (2018) 1875\u20131893. DOI:10.1007\/s10994-018-5702-8","DOI":"10.1007\/s10994-018-5702-8"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","unstructured":"Timo Nolle Stefan Luettgen Alexander Seeliger and Max M\u00fchlh\u00e4user. 2022. BINet: Multi-perspective business process anomaly classification. Information Systems 103 Article 101458 (2022) 12. DOI:10.1016\/j.is.2019.101458","DOI":"10.1016\/j.is.2019.101458"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","unstructured":"Timo Nolle Alexander Seeliger and Max M\u00fchlh\u00e4user. 2018. BINet: Multivariate business process anomaly detection using deep learning. In Business Process Management 2018 M. Weske M. Montali I. Weber and J. vom Brocke (Eds.). Springer International Publishing Cham 271\u2013287. DOI:10.1007\/978-3-319-98648-7_16","DOI":"10.1007\/978-3-319-98648-7_16"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","unstructured":"Ranjan Pal Rohan Xavier Sequeira Xinlong Yin Sander Zeijlemaker and Vineeth Kotala. 2023. How should enterprises quantify and analyze (multi-party) APT cyber-risk exposure in their industrial IoT network? ACM Transactions on Management Information Systems. Just Accepted (2023). DOI:10.1145\/3605949","DOI":"10.1145\/3605949"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","unstructured":"Marco Tulio Ribeiro Sameer Singh and Carlos Guestrin. 2016. \u201cWhy should I trust you?\u201d: Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD \u201916). ACM New York NY USA 1135\u20131144. DOI:10.1145\/2939672.2939778","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","unstructured":"A. Rozinat and W. M. P. van der Aalst. 2008. Conformance checking of processes based on monitoring real behavior. Information Systems 33 1 (2008) 64\u201395. DOI:10.1016\/j.is.2007.07.001","DOI":"10.1016\/j.is.2007.07.001"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","unstructured":"Mahdi Sahlabadi Ravie Chandren Muniyandi and Zarina Shukur. 2014. Detecting abnormal behavior in social network websites by using a process mining technique. Journal of Computer Science 10 3 (2014) 393\u2013402. DOI:10.3844\/jcssp.2014.393.402","DOI":"10.3844\/jcssp.2014.393.402"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","unstructured":"Uphar Singh Arefa Muzaffar Ranjana Vyas and O. P. Vyas. 2023. Improving event log quality using autoencoders and performing quantitative analysis with conformance checking. In Proceedings of the 13th International Conference on Cloud Computing Data Science & Engineering (Confluence). 598\u2013604. DOI:10.1109\/Confluence56041.2023.10048805","DOI":"10.1109\/Confluence56041.2023.10048805"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","unstructured":"Matthias Stierle Sven Weinzierl Maximilian Harl and Martin Matzner. 2021. A technique for determining relevance scores of process activities using graph-based neural networks. Decision Support Systems 144 Article 113511 (2021) 11. DOI:10.1016\/j.dss.2021.113511","DOI":"10.1016\/j.dss.2021.113511"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","unstructured":"Zeeshan Tariq Darryl Charles Sally McClean Ian McChesney and Paul Taylor. 2022. Anomaly detection for service-oriented business processes using conformance analysis. Algorithms 15 8 Article 257 (2022) 25. DOI:10.3390\/a15080257","DOI":"10.3390\/a15080257"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","unstructured":"Gabriel Marques Tavares and Sylvio Barbon. 2020. Analysis of language inspired trace representation for anomaly detection. In Proceedings of the ADBIS TPDL and EDA 2020 Common Workshops and Doctoral Consortium. Springer International Publishing Cham 296\u2013308. DOI:10.1007\/978-3-030-55814-7_25","DOI":"10.1007\/978-3-030-55814-7_25"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","unstructured":"Niek Tax Ilya Verenich Marcello La Rosa and Marlon Dumas. 2017. Predictive business process monitoring with LSTM neural networks. In Proceedings of the International Conference on Advanced Information Systems Engineering. Springer International Publishing Cham 477\u2013492. DOI:10.1007\/978-3-319-59536-8_30","DOI":"10.1007\/978-3-319-59536-8_30"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","unstructured":"Sven Weinzierl Sandra Zilker Jens Brunk Kate Revoredo Martin Matzner and J\u00f6rg Becker. 2020. XNAP: Making LSTM-based next activity predictions explainable by using LRP. In Proceedings of the Business Process Management Workshops. Springer International Publishing Cham 129\u2013141. DOI:10.1007\/978-3-030-66498-5_10","DOI":"10.1007\/978-3-030-66498-5_10"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","unstructured":"Bemali Wickramanayake Zhipeng He Chun Ouyang Catarina Moreira Yue Xu and Renuka Sindhgatta. 2022. Building interpretable models for business process prediction using shared and specialised attention mechanisms. Knowledge-Based Systems 248 Article 108773 (2022) 22. DOI:10.1016\/j.knosys.2022.108773","DOI":"10.1016\/j.knosys.2022.108773"}],"container-title":["ACM Transactions on Management Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3779301","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T08:56:35Z","timestamp":1773564995000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3779301"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,10]]},"references-count":35,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,3,31]]}},"alternative-id":["10.1145\/3779301"],"URL":"https:\/\/doi.org\/10.1145\/3779301","relation":{},"ISSN":["2158-656X","2158-6578"],"issn-type":[{"value":"2158-656X","type":"print"},{"value":"2158-6578","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,10]]},"assertion":[{"value":"2025-02-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}