nixtla (@nixtlainc) / X

nixtla

361 posts

nixtla

@nixtlainc

Open-source time series forecasting software.

San Francisco

Joined February 2022

nixtla
@nixtlainc
Aug 23, 2023
🎉 Update: TimeGPT (Beta) 🎉 Last week, we introduced the private beta of TimeGPT-1 – the first large pre-trained model for time series data. Original post in the comments. The response in the past 5 days has been both heartening and overwhelming. The number of requests for the
nixtla
@nixtlainc
Feb 21, 2023
🎉 We are thrilled to announce the release of the latest version of mlforecast a #Python library for Scalable #machinelearning 🤖 for #timeseries #forecasting 🚀 This version comes with exciting new features that are sure to make forecasting even more efficient and accurate 🧵
nixtla
@nixtlainc
Nov 8, 2023
We are very excited about @nixtlainc new partnership with @Microsoft . 🤯 Expect some cool new announcements soon. 🚀🎉 We feel extremely proud of the interest that TimeGPT has generated, and we are very excited to keep working hard to do our small part in contributing to time
nixtla
@nixtlainc
Jun 16, 2023
Does #transferlearning work for time series? 🤔 We created this @huggingface space so you can test on your own data and share your results. 🤗 We are working on creating the first foundational model for time series. 🤯 How should we name it? Demo:
nixtla
@nixtlainc
Aug 16, 2023
🎉🚀 Meet TimeGPT (Beta) 🤯 At Nixtla we have been working on what we think is the next big trend in our field: TimeGPT, a large and general pre-trained model for time series. We are still in private beta, but for those of you in the Bay Area, we will be hosting a conference
nixtla
@nixtlainc
Feb 28, 2023
OpenSource beats @Google's AutoML for #timeseries using #python🤯 👉 We compared BigQuery's #forecasting solution with #StatsForecast and #Fugue, concluding that BigQuery is 13% less accurate, 8 times slower and 10 times more expensive than running an #opensource alternative 🧵
nixtla
@nixtlainc
Dec 19, 2023
🎉 Introducing CoreForecast from Nixtla: blazing fast pre processing library for time series. 🌟We tested Coreforecast it against Temporain (Google) and discovered an 8x speed increase in our favor! What's more, CoreForecast, boosts speeds further through multithreading! 🚀
nixtla
@nixtlainc
Oct 5, 2023
🎉🚀📈 New release for NeuralForecast 📈🚀🎉 At Nixtla we are very excited to share the latest release of NeuralForecast, including new models, features, and tutorials 🤖💡 ⏰ Old meets New. Two new exciting models: DeepAR and TimesNet. DeepAR is one of the earliest neural
nixtla
@nixtlainc
May 21, 2024
🎉 🚀 Nixtla has partnered with @Microsoft to bring time-series forecasting to Azure 🚀 🎉 We’re beyond thrilled to share that we’re bringing our foundational time-series model TimeGPT, to @Azure enterprise-grade AI solution, optimizing it for Azure infrastructure as
nixtla
@nixtlainc
Sep 11, 2023
1/9 🧵: TimeGPT Launch Recordings Now Live! 📽️🎉 We're thrilled to share that our TimeGPT launch event recordings are now live on our brand-new YouTube channel! You can find the event playlist here: youtube.com/playlist?list=… Continue 🧵 [...]
youtube.com
TimeGPT Launch
We invite you to explore TimeGPT Beta, during this event, leading startups will showcase how they leverage TimeGPT to expand their current groundbreaking cap...
nixtla
@nixtlainc
Apr 23, 2024
🎉🚀📈 New release for StatsForecast 📈🚀🎉 We are excited to announce that the TBATS model for time series forecasting is now available in the StatsForecast library. 🔥🔥🔥 This implementation automatically selects the optimal number of Fourier terms using the method described
nixtla
@nixtlainc
Apr 25, 2024
🎉🚀📈New release for HierarchicalForecast📈🚀🎉 Tons of new features are now available in our HierarchicalForecast library! 🌲 Possibility to perform sparse reconciliation 📈 Support for probabilistic forecasting 🧠 Support for deep learning models using neuralforecast ✏
nixtla
@nixtlainc
Jun 3, 2024
🚀⚡We’re excited to announce the release of statsforecast 1.7.5.⚡ 🚀 Highlights in this release include: ✨ Addition of the MFLES model 🎁 Wrapper for scikit-learn models to leverage exogenous features StatsForecast offers a collection of widely used univariate time series
nixtla
@nixtlainc
Jul 18, 2024
🚀 We’re thrilled to announce the release of the stable version of TimeGPT! 🚀 This release takes TimeGPT out of beta and makes it broadly available to anyone for fast and easy time-series forecasting. We've added features and improvements, updated documentation, done more