neeleshbhalla/transformers_for_time_series_forecasting
Inferencing 'PatchTST' and 'Informer' to harness the power of transformers for multivariate 'long sequence time-series forecasting' (LSTF).
This project helps data analysts and researchers make highly accurate long-term predictions from complex, interconnected time-series data. It takes in historical multivariate time-series datasets and outputs reliable forecasts for future trends, enabling better planning and decision-making for various operational challenges. This is for professionals who need to predict future values from sequences of related observations.
No commits in the last 6 months.
Use this if you need to accurately forecast future trends based on long sequences of multiple related data streams, such as predicting energy consumption, traffic flow, or stock market movements.
Not ideal if you are working with short, simple time-series data or if your forecasting needs do not require state-of-the-art transformer model accuracy.
Stars
19
Forks
7
Language
Jupyter Notebook
License
—
Category
Last pushed
Nov 09, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/neeleshbhalla/transformers_for_time_series_forecasting"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
amazon-science/chronos-forecasting
Chronos: Pretrained Models for Time Series Forecasting
SalesforceAIResearch/uni2ts
Unified Training of Universal Time Series Forecasting Transformers
moment-timeseries-foundation-model/moment
MOMENT: A Family of Open Time-series Foundation Models, ICML'24
ServiceNow/TACTiS
TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series, from...
yotambraun/APDTFlow
APDTFlow is a modern and extensible forecasting framework for time series data that leverages...