Time Series Foundational Models: Their Role in Anomaly Detection and Prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908171956649984 |
|---|---|
| author | Shyalika, Chathurangi Bagga, Harleen Kaur Bhatt, Ahan Prasad, Renjith Ghazo, Alaa Al Sheth, Amit |
| author_facet | Shyalika, Chathurangi Bagga, Harleen Kaur Bhatt, Ahan Prasad, Renjith Ghazo, Alaa Al Sheth, Amit |
| contents | Time series foundational models (TSFM) have gained prominence in time series forecasting, promising state-of-the-art performance across various applications. However, their application in anomaly detection and prediction remains underexplored, with growing concerns regarding their black-box nature, lack of interpretability and applicability. This paper critically evaluates the efficacy of TSFM in anomaly detection and prediction tasks. We systematically analyze TSFM across multiple datasets, including those characterized by the absence of discernible patterns, trends and seasonality. Our analysis shows that while TSFMs can be extended for anomaly detection and prediction, traditional statistical and deep learning models often match or outperform TSFM in these tasks. Additionally, TSFMs require high computational resources but fail to capture sequential dependencies effectively or improve performance in few-shot or zero-shot scenarios. \noindent The preprocessed datasets, codes to reproduce the results and supplementary materials are available at https://github.com/smtmnfg/TSFM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_19286 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Time Series Foundational Models: Their Role in Anomaly Detection and Prediction Shyalika, Chathurangi Bagga, Harleen Kaur Bhatt, Ahan Prasad, Renjith Ghazo, Alaa Al Sheth, Amit Machine Learning Artificial Intelligence Time series foundational models (TSFM) have gained prominence in time series forecasting, promising state-of-the-art performance across various applications. However, their application in anomaly detection and prediction remains underexplored, with growing concerns regarding their black-box nature, lack of interpretability and applicability. This paper critically evaluates the efficacy of TSFM in anomaly detection and prediction tasks. We systematically analyze TSFM across multiple datasets, including those characterized by the absence of discernible patterns, trends and seasonality. Our analysis shows that while TSFMs can be extended for anomaly detection and prediction, traditional statistical and deep learning models often match or outperform TSFM in these tasks. Additionally, TSFMs require high computational resources but fail to capture sequential dependencies effectively or improve performance in few-shot or zero-shot scenarios. \noindent The preprocessed datasets, codes to reproduce the results and supplementary materials are available at https://github.com/smtmnfg/TSFM. |
| title | Time Series Foundational Models: Their Role in Anomaly Detection and Prediction |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2412.19286 |