Nixtla / nixtla
TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code π.
β2,694Updated this week
Alternatives and similar repositories for nixtla:
Users that are interested in nixtla are comparing it to the libraries listed below
- Scalable and user friendly neural forecasting algorithms.β3,441Updated this week
- Chronos: Pretrained Models for Probabilistic Time Series Forecastingβ3,175Updated last week
- Lightning β‘οΈ fast forecasting with statistical and econometric models.β4,239Updated 2 weeks ago
- Scalable machine π€ learning for time series forecasting.β1,008Updated 2 weeks ago
- Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecastingβ1,419Updated 2 months ago
- Unified Training of Universal Time Series Forecasting Transformersβ1,099Updated 3 weeks ago
- Automated Time Series Forecastingβ1,267Updated 2 weeks ago
- Foundation Models for Time Seriesβ556Updated this week
- Probabilistic Hierarchical forecasting π with statistical and econometric methods.β646Updated last week
- A toolkit for machine learning from time seriesβ1,154Updated this week
- Time series forecasting with PyTorchβ4,247Updated this week
- A unified multi-task time series model.β522Updated 6 months ago
- Time-series machine learning at scale. Built with Polars for embarrassingly parallel feature extraction and forecasts on panel data.β1,093Updated 9 months ago
- A python library for user-friendly forecasting and anomaly detection on time series.β8,505Updated this week
- Kats, a kit to analyze time series data, a lightweight, easy-to-use, generalizable, and extendable framework to perform time series analyβ¦β5,933Updated last week
- Deep learning PyTorch library for time series forecasting, classification, and anomaly detection (originally for flood forecasting).β2,166Updated this week
- Probabilistic time series modeling in Pythonβ4,839Updated last week
- Merlion: A Machine Learning Framework for Time Series Intelligenceβ4,256Updated 10 months ago
- Time series forecasting with machine learning modelsβ1,296Updated this week
- [ICLR 2025 Spotlight] Official implementation of "Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts"β559Updated 3 weeks ago
- NeuralProphet: A simple forecasting packageβ4,048Updated 3 months ago
- Collection of notebooks for time series analysisβ395Updated 3 weeks ago
- TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecastβ¦β4,576Updated last week
- [ICLR 2024] Official implementation of " π¦ Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"β1,940Updated 5 months ago
- Transfer π€ Learning for Time Series Forecastingβ246Updated 4 months ago
- A Python toolkit/library for reality-centric machine/deep learning and data mining on partially-observed time series, including SOTA neurβ¦β1,365Updated this week
- Multivariate Time Series Forecasting with efficient Transformers. Code for the paper "Long-Range Transformers for Dynamic Spatiotemporal β¦β844Updated last year
- Resources about time series forecasting and deep learning.β642Updated this week
- An offical implementation of PatchTST: "A Time Series is Worth 64 Words: Long-term Forecasting with Transformers." (ICLR 2023) https://arβ¦β1,888Updated 8 months ago
- A comprehensive survey on the time series domainsβ524Updated last year