lqzxt/Time-R1

Time-R1 is a two-stage reinforcement fine-tuning framework that trains large language models to perform slow-thinking, step-by-step reasoning for accurate and explainable time series forecasting.

39
/ 100
Emerging

This project helps data scientists and analysts make more accurate future predictions from their time series data, such as sales figures, stock prices, or sensor readings. It takes your historical time series data as input and produces highly accurate forecasts, along with the step-by-step reasoning behind those predictions. It's designed for professionals who need reliable, explainable forecasts for decision-making.

Use this if you are a data scientist or analyst looking to significantly improve the accuracy and explainability of your time series forecasts using a sophisticated, 'slow-thinking' AI approach.

Not ideal if you need a quick, off-the-shelf forecasting solution without diving into advanced AI model training or have limited computational resources for large language model fine-tuning.

time-series-forecasting predictive-analytics financial-forecasting demand-planning operations-optimization
No License No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 7 / 25
Community 13 / 25

How are scores calculated?

Stars

94

Forks

11

Language

Python

License

Last pushed

Jan 28, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/lqzxt/Time-R1"

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