yyalau/iclr2025_dsof

This is the official repository for the ICLR 2025 Conference Paper - Fast and Slow Streams for Online Time Series Forecasting without Information Leakage.

26
/ 100
Experimental

This project offers an advanced method for predicting future values in time series data, specifically designed for real-time situations where data arrives continuously. It takes historical time series observations (like electricity consumption or traffic flow) and produces accurate forecasts for multiple steps into the future. This tool is for researchers and practitioners working on developing and evaluating state-of-the-art online forecasting models.

No commits in the last 6 months.

Use this if you need to perform online time series forecasting where predictions are continuously updated as new data arrives, and you want to avoid common issues like data leakage and overfitting to recent noise.

Not ideal if you are looking for a simple, out-of-the-box forecasting solution without needing to engage with advanced model configuration or academic research settings.

time-series-forecasting online-learning predictive-modeling real-time-analytics machine-learning-research
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

15

Forks

2

Language

Python

License

Last pushed

Apr 30, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yyalau/iclr2025_dsof"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.