Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Can it work on anomaly detection? #12

Open
puyiwen opened this issue Dec 19, 2024 · 1 comment
Open

Can it work on anomaly detection? #12

puyiwen opened this issue Dec 19, 2024 · 1 comment

Comments

@puyiwen
Copy link

puyiwen commented Dec 19, 2024

Hi, I am a new one in time series data analysis. Can this model be used for anomaly detection? If so, what codes do I need to modify to anomaly detection? Thank you very much!

@lss-1138
Copy link
Owner

Hi, SparseTSF is designed for long-term time series forecasting tasks. It downsamples both the input and output sequences.

If you want to use it for anomaly detection (for example, detecting anomalies based on reconstruction errors of the input sequence), you would need to change the output target sequence to the input itself, and also customize the anomaly score threshold.

For a simpler implementation, you can try embedding it directly into TSLib, which provides the full anomaly detection pipeline.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants