TDSRL: Time Series Dual Self-Supervised Representation Learning for Anomaly Detection from Different Perspectives

Yongsheng Dai, Hui Wang, Karen Rafferty, Ivor Spence and Barry Quinn

No 2024/03, QBS Working Paper Series from Queen's University Belfast, Queen's Business School

Abstract: Time series anomaly detection plays a critical role in various applications, from finance to industrial monitoring. Effective models need to capture both the inherent characteristics of time series data and the unique patterns associated with anomalies. While traditional forecasting-based and reconstruction-based approaches have been successful, they tend to struggle with complex and evolving anomalies. For instance, stock market data exhibits complex and ever-changing fluctuation patterns that defy straightforward modelling. In this paper, we propose a novel approach called TDSRL (Time Series Dual Self-Supervised Representation Learning) for robust anomaly detection. TDSRL leverages synthetic anomaly segments which are artificially generated to simulate real-world anomalies. The key innovation lies in dual self-supervised pretext tasks: one task characterises anomalies in relation to the entire time series, while the other focuses on local anomaly boundaries. Additionally, we introduce a data degradation method that operates in both the time and frequency domains, creating a more natural simulation of real-world anomalies compared to purely synthetic data. Consequently, TDSRL is expected to achieve more accurate predictions of the location and extent of anomalous segments. Our experiments demonstrate that TDSRL outperforms state-of-the-art methods, making it a promising avenue for time series anomaly detection.

Keywords: Time series anomaly detection; self-supervised representation learning; contrastive learning; synthetic anomaly (search for similar items in EconPapers)
Date: 2024
New Economics Papers: this item is included in nep-big, nep-cmp, nep-ecm and nep-ets
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.econstor.eu/bitstream/10419/289582/1/wps-2024-03.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:zbw:qmsrps:202403

Access Statistics for this paper

More papers in QBS Working Paper Series from Queen's University Belfast, Queen's Business School Contact information at EDIRC.
Bibliographic data for series maintained by ZBW - Leibniz Information Centre for Economics ().