{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T04:36:08Z","timestamp":1782880568268,"version":"3.54.5"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T00:00:00Z","timestamp":1720742400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T00:00:00Z","timestamp":1720742400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100008815","name":"Libera Universit\u00e0 di Bolzano","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100008815","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Data Sci Anal"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Machine learning is used widely to create a range of prediction or classification models. The quality of the machine learning (ML) models depends not only on the model creation process, but also on the input data quality. We investigate here the impact of data quality on the quality of the ML model in a generic way. The aim is to identify a possible data quality problem based on observed anomalies in the ML model over time. This is achieved in the form of a root cause analysis of anomalies detected in the ML model. We develop a generic anomaly detection and analysis framework and demonstrate its application to two prediction scenarios based on sensor data.<\/jats:p>","DOI":"10.1007\/s41060-024-00593-y","type":"journal-article","created":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T13:02:05Z","timestamp":1720789325000},"page":"155-180","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Anomaly analytics in data-driven machine learning applications"],"prefix":"10.1007","volume":"19","author":[{"given":"Shelernaz","family":"Azimi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claus","family":"Pahl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,7,12]]},"reference":[{"key":"593_CR1","doi-asserted-by":"crossref","unstructured":"Azimi, S., Pahl, C.: Root cause analysis and remediation for quality and value improvement in machine learning driven information models. In: 22nd International Conference on Enterprise Information Systems\u2014ICEIS 2020. SciTePress (2020)","DOI":"10.5220\/0009783106560665"},{"key":"593_CR2","doi-asserted-by":"crossref","unstructured":"Azimi, S., Pahl, C.: Continuous data quality management for machine learning based data-as-a-service architectures. In: Proceedings of the 11th International Conference on Cloud Computing and Services Science\u2014CLOSER, pp. 328\u2013335. SciTePress (2021)","DOI":"10.5220\/0010509503280335"},{"issue":"2","key":"593_CR3","doi-asserted-by":"publisher","first-page":"218","DOI":"10.26421\/JDI3.2-2","volume":"3","author":"S Azimi","year":"2022","unstructured":"Azimi, S., Pahl, C.: The impact of data completeness and correctness on explainable machine learning models. J. Data Intell. 3(2), 218\u2013231 (2022)","journal-title":"J. Data Intell."},{"key":"593_CR4","doi-asserted-by":"crossref","unstructured":"Bahri, M., Salutari, F., Putina, A., et\u00a0al. AutoML: state of the art with a focus on anomaly detection, challenges, and research directions. Int. J. Data Sci. Anal. (2022)","DOI":"10.1007\/s41060-022-00309-0"},{"key":"593_CR5","doi-asserted-by":"crossref","unstructured":"Bhowmik, P.: Machine learning in production: From experimented ml model to system. ScienceOpen Preprints (2022)","DOI":"10.14293\/S2199-1006.1.SOR-.PPKHXND.v1"},{"key":"593_CR6","doi-asserted-by":"crossref","unstructured":"Chandola, V., Banerjee, A., Kumar, V.: Anomaly detection: a survey. ACM Comput. Surv. 41(3) (2009)","DOI":"10.1145\/1541880.1541882"},{"key":"593_CR7","unstructured":"De\u00a0Hoog, J., Mercelis, S., Hellinckx, P.: Improving machine learning-based decision-making through inclusion of data quality. In: CEUR Workshop Proceedings 2491 (2019)"},{"key":"593_CR8","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/978-3-030-27615-7_17","volume-title":"Database and Expert Systems Applications","author":"L Ehrlinger","year":"2019","unstructured":"Ehrlinger, L., Haunschmid, V., Palazzini, D., et al.: A DAQL to monitor data quality in machine learning applications. In: Hartmann, S., K\u00fcng, J., Chakravarthy, S., et al. (eds.) Database and Expert Systems Applications, pp. 227\u2013237. Springer, Cham (2019)"},{"key":"593_CR9","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.ins.2019.03.013","volume":"487","author":"C Eiras-Franco","year":"2019","unstructured":"Eiras-Franco, C., Mart\u00ednez-Rego, D., Guijarro-Berdi\u00f1as, B., et al.: Large scale anomaly detection in mixed numerical and categorical input spaces. Inf. Sci. 487, 115\u2013127 (2019)","journal-title":"Inf. Sci."},{"key":"593_CR10","unstructured":"Even, A., Shankaranarayanan, G.: Value-driven data quality assessment. In: 10th International Conference on Information Quality, ICIQ (2005)"},{"issue":"4","key":"593_CR11","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1007\/s41060-021-00265-1","volume":"12","author":"R Foorthuis","year":"2021","unstructured":"Foorthuis, R.: On the nature and types of anomalies: a review of deviations in data. Int. J. Data Sci. Anal. 12(4), 297\u2013331 (2021)","journal-title":"Int. J. Data Sci. Anal."},{"issue":"106","key":"593_CR12","first-page":"622","volume":"212","author":"X He","year":"2021","unstructured":"He, X., Zhao, K., Chu, X.: Automl: a survey of the state-of-the-art. Knowl.-Based Syst. 212(106), 622 (2021)","journal-title":"Knowl.-Based Syst."},{"issue":"2","key":"593_CR13","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1023\/B:AIRE.0000045502.10941.a9","volume":"22","author":"V Hodge","year":"2004","unstructured":"Hodge, V., Austin, J.: A survey of outlier detection methodologies. Artif. Intell. Rev. 22(2), 85\u2013126 (2004)","journal-title":"Artif. Intell. Rev."},{"key":"593_CR14","doi-asserted-by":"crossref","unstructured":"Hwang, W.S., Yun, J.H., Kim, J., et\u00a0al. Time-series aware precision and recall for anomaly detection: considering variety of detection result and addressing ambiguous labeling. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management (2019)","DOI":"10.1145\/3357384.3358118"},{"key":"593_CR15","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Li, X., Luo, H., et al.: Quo vadis artificial intelligence? Discover Artif. Intell. 2(1), 4 (2022)","DOI":"10.1007\/s44163-022-00022-8"},{"key":"593_CR16","doi-asserted-by":"crossref","unstructured":"Kotlar, M., Punt, M., Radivojevi\u0107, Z., et al.: Novel meta-features for automated machine learning model selection in anomaly detection. IEEE Access 9, 89675\u201389687 (2021)","DOI":"10.1109\/ACCESS.2021.3090936"},{"key":"593_CR17","doi-asserted-by":"crossref","unstructured":"Li, J., Izakian, H., Pedrycz, W., et al.: Clustering-based anomaly detection in multivariate time series data. Appl. Soft Comput. 100(106), 919 (2021)","DOI":"10.1016\/j.asoc.2020.106919"},{"issue":"103","key":"593_CR18","first-page":"153","volume":"43","author":"X Li","year":"2021","unstructured":"Li, X., Liu, J., Liu, B., et al.: Impacts of data uncertainty on the performance of data-driven-based building fault diagnosis. J. Build. Eng. 43(103), 153 (2021)","journal-title":"J. Build. Eng."},{"key":"593_CR19","doi-asserted-by":"crossref","unstructured":"Lwakatare, L.E., Raj, A., Bosch, J., et\u00a0al. A taxonomy of software engineering challenges for machine learning systems: An empirical investigation. In: Agile Processes in Software Engineering and Extreme Programming\u201420th International Conference (2019)","DOI":"10.1007\/978-3-030-19034-7_14"},{"key":"593_CR20","unstructured":"Marev, M.S., Compatangelo, E., Vasconcelos, W.W.: Towards a context-dependent numerical data quality evaluation framework. CoRR abs\/1810.09399 (2018)"},{"key":"593_CR21","doi-asserted-by":"publisher","first-page":"48231","DOI":"10.1109\/ACCESS.2018.2863036","volume":"6","author":"S Naseer","year":"2018","unstructured":"Naseer, S., Saleem, Y., Khalid, S., et al.: Enhanced network anomaly detection based on deep neural networks. IEEE Access 6, 48231\u201348246 (2018)","journal-title":"IEEE Access"},{"key":"593_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11761-022-00352-6","volume":"17","author":"C Pahl","year":"2022","unstructured":"Pahl, C.: Research challenges for machine learning-constructed software. SOCA 17, 1\u20134 (2022)","journal-title":"SOCA"},{"issue":"6","key":"593_CR23","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1109\/MS.2021.3067940","volume":"38","author":"C Pahl","year":"2021","unstructured":"Pahl, C., Azimi, S.: Constructing dependable data-driven software with machine learning. IEEE Softw. 38(6), 88\u201397 (2021)","journal-title":"IEEE Softw."},{"issue":"1","key":"593_CR24","first-page":"29","volume":"2","author":"M Pradhan","year":"2012","unstructured":"Pradhan, M., Pradhan, S.K., Sahu, S.K.: Anomaly detection using artificial neural network. Int. J. Eng. Sci. Emerg. Technol. 2(1), 29\u201336 (2012)","journal-title":"Int. J. Eng. Sci. Emerg. Technol."},{"key":"593_CR25","first-page":"2584","volume-title":"AutoAI-TS: AutoAI for Time Series Forecasting","author":"SY Shah","year":"2021","unstructured":"Shah, S.Y., Patel, D., Vu, L., et al.: AutoAI-TS: AutoAI for Time Series Forecasting, pp. 2584\u20132596. Association for Computing Machinery, New York (2021)"},{"key":"593_CR26","unstructured":"Tatbul, N., Lee, T.J., Zdonik, S., et\u00a0al. Precision and recall for time series. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"593_CR27","doi-asserted-by":"crossref","unstructured":"Vinzamuri, B., Khabiri, E., Bhamidipaty, A., et\u00a0al. An end-to-end context aware anomaly detection system. In: 2020 IEEE International Conference on Big Data (Big Data), pp. 1689\u20131698 (2020)","DOI":"10.1109\/BigData50022.2020.9377767"},{"key":"593_CR28","doi-asserted-by":"publisher","first-page":"139712","DOI":"10.1109\/ACCESS.2019.2943667","volume":"7","author":"X Wang","year":"2019","unstructured":"Wang, X., Yang, I., Ahn, S.H.: Sample efficient home power anomaly detection in real time using semi-supervised learning. IEEE Access 7, 139712\u2013139725 (2019)","journal-title":"IEEE Access"},{"key":"593_CR29","unstructured":"Wen, T., Keyes, R.: Time series anomaly detection using convolutional neural networks and transfer learning. CoRR abs\/1905.13628. arXiv:1905.13628 (2019)"},{"key":"593_CR30","unstructured":"Wheeler, W.: Evaluating anomaly detection algorithms with precision-recall curves. https:\/\/medium.com\/wwblog\/evaluating-anomaly-detection-algorithms-with-precision-recall-curves-f3eb5b679476 (2018)"},{"issue":"109","key":"593_CR31","first-page":"546","volume":"180","author":"L Xie","year":"2021","unstructured":"Xie, L., Pi, D., Zhang, X., et al.: Graph neural network approach for anomaly detection. Measurement 180(109), 546 (2021)","journal-title":"Measurement"},{"key":"593_CR32","first-page":"1","volume-title":"Encyclopedia of Database Systems","author":"A Zimek","year":"2017","unstructured":"Zimek, A., Schubert, E.: Outlier detection. In: Liu, L., \u00d6zsu, M.T. (eds.) Encyclopedia of Database Systems, pp. 1\u20135. Springer, New York (2017)"}],"container-title":["International Journal of Data Science and Analytics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-024-00593-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41060-024-00593-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-024-00593-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T10:52:43Z","timestamp":1737715963000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41060-024-00593-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,12]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["593"],"URL":"https:\/\/doi.org\/10.1007\/s41060-024-00593-y","relation":{},"ISSN":["2364-415X","2364-4168"],"issn-type":[{"value":"2364-415X","type":"print"},{"value":"2364-4168","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,12]]},"assertion":[{"value":"17 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 June 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No conflict of interest of a financial or personal nature exists.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}