zqiao11/MSFT

Multi-scale Finetuning for Encoder-based Time Series Foundation Models

28
/ 100
Experimental

This tool helps researchers and data scientists working with time series data to improve the accuracy of their forecasting models. It takes pre-existing time series foundation models and specific datasets, then applies a multi-scale fine-tuning process to produce more effective forecasting models. This is ideal for those who need to make precise predictions based on historical sequences, like financial trends or energy consumption.

No commits in the last 6 months.

Use this if you are a researcher or data scientist looking to enhance the predictive power of time series foundation models for specific forecasting tasks by addressing scale differences in your data.

Not ideal if you are a business user without a background in machine learning or if you need a plug-and-play solution without fine-tuning existing models.

time-series-forecasting predictive-analytics machine-learning-research data-science model-optimization
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 6 / 25

How are scores calculated?

Stars

13

Forks

1

Language

Python

License

Last pushed

Sep 23, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zqiao11/MSFT"

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