mala-lab/SEMPO

[NeurIPS 2025] Official implementation of "SEMPO: Lightweight Foundation Models for Time Series Forecasting"

42
/ 100
Emerging

This project helps operations engineers, financial analysts, or supply chain managers predict future trends from time-series data. It takes your historical time-series data, like sales figures or sensor readings, and produces highly accurate forecasts. This is ideal for anyone needing to make predictions with limited historical data or computational resources.

Use this if you need to accurately forecast future values from diverse time-series data, even when you have smaller datasets or want to conserve computational power.

Not ideal if you primarily work with static, non-sequential datasets for tasks like classification or regression, as this is specifically designed for time-series forecasting.

time-series-forecasting demand-planning operations-management financial-forecasting predictive-maintenance
No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 15 / 25
Community 15 / 25

How are scores calculated?

Stars

18

Forks

4

Language

Python

License

Apache-2.0

Last pushed

Oct 23, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/mala-lab/SEMPO"

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