Abstract
Detecting anomalies in time series has become increasingly challenging as data collection technology develops, especially in real-world communication services, which require contextual information for precise prediction. To address this challenge, researchers usually use time-series decomposition to reveal underlying patterns, e.g., trends and seasonality. However, existing decomposition-based anomaly detectors do not explicitly consider such contextual information, limiting their ability to correctly detect contextual cases. This paper proposes Time-CAD, a new context-aware deep time-series decomposition framework to detect anomalies for a more practical scenario in real-world businesses. We verify the effectiveness of the novel design for integrating contextual information into deep time-series decomposition through extensive experiments on four real-world benchmarks, demonstrating improvements of up to \(46\%\) in time-series aware \(F_1\) score on average.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
A univariate time series is a special case of a multivariate time series when \(M=1\).
- 2.
- 3.
- 4.
- 5.
References
Abdulaal, A., Liu, Z., Lancewicki, T.: Practical approach to asynchronous multivariate time series anomaly detection and localization. In: ACM SIGKDD (2021)
Audibert, J., Michiardi, P., Guyard, F., Marti, S., Zuluaga, M.A.: USAD: unsupervised anomaly detection on multivariate time series. In: ACM SIGKDD (2020)
Bergmann, P., Löwe, S., Fauser, M., Sattlegger, D., Steger, C.: Improving unsupervised defect segmentation by applying structural similarity to autoencoders. arXiv:1807.02011 (2018)
Blázquez-García, A., Conde, A., Mori, U., Lozano, J.A.: A review on outlier/anomaly detection in time series data. ACM CSUR 54(3) (2021)
Braei, M., Wagner, S.: Anomaly detection in univariate time-series: a survey on the state-of-the-art. arXiv:2004.00433 (2020)
Breunig, M.M., Kriegel, H.P., Ng, R.T., Sander, J.: LOF: identifying density-based local outliers. In: ACM SIGMOD (2000)
Chandola, V.: Anomaly Detection for Symbolic Sequences and Time Series Data. University of Minnesota (2009)
Cho, K., et al.: Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv:1406.1078 (2014)
Choi, K., Yi, J., Park, C., Yoon, S.: Deep learning for anomaly detection in time-series data: Review, analysis, and guidelines. IEEE Access (2021)
Cleveland, R.B., Cleveland, W.S., McRae, J.E., Terpenning, I.: STL: A seasonal-trend decomposition. J. Off. Stat 6(1) (1990)
Darban, Z.Z., Webb, G.I., Pan, S., Aggarwal, C.C., Salehi, M.: Deep learning for time series anomaly detection: a survey. arXiv:2211.05244 (2022)
Ester, M., Kriegel, H.P., Sander, J., Xu, X., et al.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: ACM SIGKDD (1996)
Farshchi, M., et al.: Contextual anomaly detection for a critical industrial system based on logs and metrics. In: EDCC (2018)
Feng, C., Tian, P.: Time series anomaly detection for cyber-physical systems via neural system identification and bayesian filtering. In: ACM SIGKDD (2021)
Garg, A., Zhang, W., Samaran, J., Savitha, R., Foo, C.S.: An evaluation of anomaly detection and diagnosis in multivariate time series. IEEE Trans. Neural Netw. Learn. Syst. (2021)
Hawkins, D.M.: Identification of Outliers, vol. 11. Springer (1980). https://doi.org/10.1007/978-94-015-3994-4
Hochenbaum, J., Vallis, O.S., Kejariwal, A.: Automatic anomaly detection in the cloud via statistical learning. arXiv:1704.07706 (2017)
Hwang, W.S., Yun, J.H., Kim, J., Kim, H.C.: Time-series aware precision and recall for anomaly detection: Considering variety of detection result and addressing ambiguous labeling. In: CIKM (2019)
Kieu, T., Yang, B., Guo, C., Jensen, C.S.: Outlier detection for time series with recurrent autoencoder ensembles. In: IJCAI (2019)
Li, Z., et al.: Multivariate time series anomaly detection and interpretation using hierarchical inter-metric and temporal embedding. In: ACM SIGKDD (2021)
Liu, F.T., Ting, K.M., Zhou, Z.H.: Isolation forest. In: IEEE ICDM (2008)
Moustafa, N.: A new distributed architecture for evaluating ai-based security systems at the edge: network ton_iot datasets. SCS 72 (2021)
Ren, H., et al.: Time-series anomaly detection service at microsoft. In: ACM SIGKDD (2019)
Rousseeuw, P.J., Leroy, A.M.: Robust Regression and Outlier Detection, vol. 589. John wiley & sons (2005)
Schölkopf, B., et al.: Support vector method for novelty detection. In: NeurIPS (1999)
Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45(11) (1997)
Shen, L., Li, Z., Kwok, J.: Timeseries anomaly detection using temporal hierarchical one-class network. In: NeurIPS (2020)
Shen, L., Yu, Z., Ma, Q., Kwok, J.T.: Time series anomaly detection with multiresolution ensemble decoding. In: AAAI (2021)
Su, Y., Zhao, Y., Niu, C., Liu, R., Sun, W., Pei, D.: Robust anomaly detection for multivariate time series through stochastic recurrent neural network. In: ACM SIGKDD (2019)
Taylor, S.J., Letham, B.: Forecasting at scale. Am. Stat. 72(1) (2018)
Theodosiou, M.: Forecasting monthly and quarterly time series using stl decomposition. Int. J. Forecast. 27(4) (2011)
Tuli, S., Casale, G., Jennings, N.R.: TranAD: deep transformer networks for anomaly detection in multivariate time series data. VLDB Endow. 15(6), 1201–1214 (2022)
Wen, Q., Gao, J., Song, X., Sun, L., Xu, H., Zhu, S.: RobustSTL: a robust seasonal-trend decomposition algorithm for long time series. In: AAAI (2019)
Wen, Q., Zhang, Z., Li, Y., Sun, L.: Fast RobustSTL: efficient and robust seasonal-trend decomposition for time series with complex patterns. In: ACM SIGKDD (2020)
Xu, H., et al.: Unsupervised anomaly detection via variational auto-encoder for seasonal KPIs in web applications. In: WWW (2018)
Xu, J., Wu, H., Wang, J., Long, M.: Anomaly transformer: time series anomaly detection with association discrepancy. In: ICLR (2022)
Yoo, Y.H., Kim, U.H., Kim, J.H.: Recurrent reconstructive network for sequential anomaly detection. In: IEEE CYB (2019)
Zhang, C., Zhou, T., Wen, Q., Sun, L.: TFAD: a decomposition time series anomaly detection architecture with time-frequency analysis. In: CIKM, pp. 2497–2507 (2022)
Zhang, C., et al.: A deep neural network for unsupervised anomaly detection and diagnosis in multivariate time series data. In: AAAI (2019)
Zhao, H., et al.: Multivariate time-series anomaly detection via graph attention network. In: IEEE ICDM (2020)
Zhou, B., Liu, S., Hooi, B., Cheng, X., Ye, J.: BeatGAN: anomalous rhythm detection using adversarially generated time series. In: IJCAI, pp. 4433–4439 (2019)
Acknowledgments
This work was partly supported by Mobile eXperience Business, Samsung Electronics Co., Ltd. (Real-time Service Incident Prediction Development) and the National Research Foundation of Korea (NRF) grant funded by the Korea government (Ministry of Science and ICT) (No. 2023R1A2C 2003690).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Ethical Statement
This work adheres to ethical standards and guidelines for scientific research. We use publicly available datasets and obtain all necessary permissions and approvals before conducting the experiments and data collection. Therefore, we ensure the privacy and anonymity of all human participants involved in the data collection process. In particular, the RCS and KPI datasets are the communication service datasets significantly associated with real users. Both RCS and KPI datasets were completely anonymized with their types and features before we received them. Our research aims to advance the field of anomaly detection having critical applications in various domains, such as finance, healthcare, and cyber security. However, there might be potential malicious impacts when inappropriately using our work. For example, the advancement and findings from Time-CAD might be adversely exploited for devising more subtle and sophisticated attacks or deceptions.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Nam, Y., Trirat, P., Kim, T., Lee, Y., Lee, JG. (2023). Context-Aware Deep Time-Series Decomposition for Anomaly Detection in Businesses. In: De Francisci Morales, G., Perlich, C., Ruchansky, N., Kourtellis, N., Baralis, E., Bonchi, F. (eds) Machine Learning and Knowledge Discovery in Databases: Applied Data Science and Demo Track. ECML PKDD 2023. Lecture Notes in Computer Science(), vol 14174. Springer, Cham. https://doi.org/10.1007/978-3-031-43427-3_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-43427-3_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43426-6
Online ISBN: 978-3-031-43427-3
eBook Packages: Computer ScienceComputer Science (R0)
