ServiceNow/TACTiS
TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series, from ServiceNow Research
This project helps data scientists and machine learning engineers analyze complex real-world data that changes over time, like economic indicators or sensor readings. It takes in multivariate time series data, even if it's incomplete or unevenly recorded, and produces probabilistic predictions for future values or fills in missing gaps. This allows users to understand the likely range of outcomes for various interconnected metrics.
139 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to accurately forecast or interpolate values for multiple interrelated time series datasets, especially if your data is noisy or has missing points.
Not ideal if your data is not time-series based or if you only need simple point forecasts without understanding the probability distribution of outcomes.
Stars
139
Forks
25
Language
Python
License
Apache-2.0
Category
Last pushed
May 03, 2024
Commits (30d)
0
Dependencies
5
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ServiceNow/TACTiS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
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
yotambraun/APDTFlow
APDTFlow is a modern and extensible forecasting framework for time series data that leverages...
Thinklab-SJTU/Crossformer
Official implementation of our ICLR 2023 paper "Crossformer: Transformer Utilizing...