#TimeGPT
LightNews LightNews
what-a-mass.bsky.social
The TimeGPT muscle growth sequence is fully done ✨ there's 2 more alts to all 5 pictures available ✨
August 30, 2025 at 10:45 PM
ramikrispin.bsky.social
Holy 🐮, TIL that Nixtla has R version - nixtlar!

nixtla.github.io/nixtlar/inde...

#rstats #machinelearning #timeseries
A Software Development Kit for Nixtla's TimeGPT
A Software Development Kit for working with Nixtla's TimeGPT, a foundation model for time series forecasting. API is an acronym for application programming interface; this package allows users to inte...
nixtla.github.io
November 28, 2024 at 3:41 PM
martinstein.bsky.social
Great Time Series review by Joseph Rickert.

He shows TimeGPT using nixtlar. I would love to see more use cases with different data sets.

Who's next?

#TimeSeries #rstats #TimeGPT #nixtlar

rworks.dev/posts/revise...
A First Look at TimeGPT using nixtlar – R Works
TimeGPT is a pre-trained, multi-layer, encoder/decoder transformer model with self-attention mechansims designed specifically for time series forecasting. This post, a revision of the of the post firs...
rworks.dev
February 20, 2025 at 2:03 PM
revojoe.bsky.social
Experimenting with TimeGPT, the new transformer model trained on time series data from Nixtla, is straightforward with the nixtlar #rstats package. See rworks.dev/posts/TimeGPT/
A First Look at TimeGPT using nixtlar – R Works
TimeGPT is a pre-trained, multi-layer, encoder/decoder transformer model with self-attention mechansims designed specifically for time series forecasting. This post is a first look at forecsting with ...
rworks.dev
February 13, 2025 at 6:32 PM
frankiethull.bsky.social
nixtlar uses TimeGPT -- which is a really amazing foundational model for time series!
ramikrispin.bsky.social Rami Krispin @ramikrispin.bsky.social · Dec 6
Forecasting with foundation models in R 🚀

In this week's edition of my newsletter, I reviewed the nixtlar library. The nixtlar is a new R library from Nixtla, developed by Mariana Menchero. 🧵👇🏼 1/3

#RStats #forecasting #AI #DataScience
December 6, 2024 at 5:00 PM
ramikrispin.bsky.social
I am excited to present this Thursday, March 13, at the Bay Area useR meetup about analyzing time series data at scale with cluster analysis methods.

Mariana Menchero, the author of the nixtlar R library from Nixtla, will present about forecasting foundation models using TimeGPT 🚀!

#RStats
March 12, 2025 at 2:32 PM
eschmiegelow.bsky.social
Until recently, time series prediction was heavily reliant on traditional ML, with TimeGPT transformers are making their way into that domain.

medium.com/@andrepedrin...
From ARIMA to TimeGPT — A New Era in Time Series Prediction (Part I)
Innovative Approaches to Enhance Time Series Forecasting with TimeGPT
medium.com
November 27, 2024 at 6:48 AM
lordelago.bsky.social
Más vale que se llame TimeGPT
xabibenputa.bsky.social Xabibenputa @xabibenputa.bsky.social · Aug 3
He descubierto una máquina que es capaz de viajar en el tiempo.
August 3, 2026 at 2:28 PM
ramikrispin.bsky.social
Forecasting with Nixtla 🚀

A great episode of the AI Stories podcast about time series forecasting. Neil Leiser hosts Max Mergenthaler Canseco CEO and Co-founder of Nixtla.

youtu.be/6teB04OwhJg

#nixtla #datascience #forecasting #machinelearning #python
TimeGPT, Nixtla & Forecasting with Max Mergenthaler #53
YouTube video by AI Stories Podcast - Neil Leiser
youtu.be
December 11, 2024 at 2:44 PM
Préparez-vous à plonger dans le futur avec TimeGPT ! 🎉 Cette IA analyse vos données pour des prédictions ultra-précises. 🚀💡 #IA #Innovation #Tech

TimeGPT – L’IA qui prédit l’avenir
TimeGPT est un modèle d’IA révolutionnaire capable de prédire avec précision les séries temporelles. Découvrez comment cette avancée majeure en apprentissage profond peut transformer divers d…
korben.info
May 23, 2024 at 7:05 AM
ramikrispin.bsky.social
(2/3) The library provides an interface to Nixtla's TimeGPT - a foundation model for time series forecasting applications. In addition to forecasting applications, the TimeGPT provides applications for anomaly detection.

Source code: github.com/Nixtla/nixtlar
GitHub - Nixtla/nixtlar: R SDK for TimeGPT
R SDK for TimeGPT. Contribute to Nixtla/nixtlar development by creating an account on GitHub.
github.com
December 6, 2024 at 4:44 PM
qdrddr.bsky.social
pre-trained #TimeSeries Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points.

Apache 2.0 lic
#OpenSource #LLM #AI

github.com/Nixtla/nixtla
GitHub - 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 1...
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&#...
github.com
December 8, 2025 at 11:25 PM
newsycombinator.bsky.social
TimeGPT-1 (arxiv.org)

Main Link | HN Post
October 13, 2023 at 8:21 PM
opensourceposter.bsky.social
Hot take: Is AI killing old forecasting? Discover how time series, TimeGPT & Data NFTs disrupt finance, healthcare & energy. Dive: https://dev.to/jennythomas498/ai-and-time-series-data-harnessing-temporal-insights-in-a-digital-age-4ea3
April 12, 2025 at 6:33 AM
mockingdog.bsky.social
LLM毕竟不是为数理预测优化的。transformer 这个架构本身是可以做预测的，比如之前有个 TimeGPT (GPT， 或者说 decoder only transformer 本身就是个 masked auto regressive model)
October 27, 2025 at 3:53 AM
opensourceposter.bsky.social
How can AI truly transform time series data? This article dives into large models, controversial NFT monetization, and the power of predictive analytics. Ready to challenge the status quo? https://www.license-token.com/wiki/ai-time-series-data-timegpt
April 5, 2025 at 11:33 AM
ai-news.at.thenote.app
Prophet vs NeuralProphet vs TimeGPT vs Chronos: A Practical Comparison

Time series forecasting predicts future values by learning patterns from past data. It is widely used in sales, finance, energy, web traffic, inventory planning, and business decision-making. Bu…

Telegram AI Digest
#ai #gpt #ml
Prophet vs NeuralProphet vs TimeGPT vs Chronos: A Practical Comparison
Time series forecasting predicts future values by learning patterns from past data. It is widely used in sales, finance, energy, web traffic, inventory planning, and business decision-making. But a lot has changed since the advent of advance ML models. Forecasting has moved from traditional statistical models to neural and foundation-model approaches. Tools like Prophet, NeuralProphet, […]
www.analyticsvidhya.com
June 10, 2026 at 11:27 AM
revojoe.bsky.social
If you are in the Bay Area, don't miss the opportunity to hear Mariana Menchero, author of the nixtlar package for the TimeGPT, time series transform model, and Apple data scientist Rami Krispin talk about time series modeling with #rstats at the March BARUG meeting.
www.meetup.com/r-users/even...
BARUG March 2025 Meeting, Thu, Mar 13, 2025, 6:30 PM | Meetup
The meeting is still coming together, but we are excited to announce our first meetup of the year. Please mark Thursday evening, March 13 on your calendar. Agenda: 6:30 Pi
www.meetup.com
February 18, 2025 at 8:51 PM
druce.ai
OpenAI arms devs with AI conversation tool that can talk and listen at the same timeGPT-Live-1 makes speaking to AI models more fluid
OpenAI arms devs with AI conversation tool that can talk and listen at the same time
GPT-Live-1 makes speaking to AI models more fluid
www.theregister.com
September 11, 2026 at 1:06 PM
natalie-reed.bsky.social
Nixtla built ChatGPT's cousin for the future - TimeGPT forecasts time series in three lines of code.

https://yespress.io/nixtla?utm_source=bluesky&utm_medium=social via Yespress - apply for company newsroom: yespress.io/newsroom
Nixtla - The Company That Turned Forecasting Into an Import Statement
Nixtla built TimeGPT, a foundation model for time-series forecasting. From 68M+ open-source downloads to a $16M Series A.
yespress.io
August 16, 2026 at 4:12 AM
ai-ru.at.thenote.app
Пророк против НейроПророка против TimeGPT против Хроноса: Практическое сравнение

Прогнозирование временных рядов предсказывает будущие значения, изучая закономерности из прошлых данных. Оно широко используется в продажах, финансах, энергетике, веб-трафике, план…

Telegram ИИ Дайджест
#ai #gpt #news
Prophet vs NeuralProphet vs TimeGPT vs Chronos: A Practical Comparison
www.analyticsvidhya.com
June 10, 2026 at 11:23 AM
techfr.skyfleet.blue
TimeGPT – L’IA qui prédit l’avenir
TimeGPT – L’IA qui prédit l’avenir
TimeGPT est un modèle d’IA révolutionnaire capable de prédire avec précision les séries temporelles. Découvrez comment cette avancée majeure en apprentissage profond peut transformer divers d…
korben.info
May 23, 2024 at 7:41 AM
paperposterbot.bsky.social
arXiv📈🤖
IISE PG&E Energy Analytics Challenge 2025: Hourly-Binned Regression Models Beat Transformers in Load Forecasting
By Roy, Pyltsov, Hu
Accurate electricity load forecasting is essential for grid stability, resource optimization, and renewable energy integration. While transformer-based deep learning models like TimeGPT have gained traction in time-series forecasting, their effectiveness in long-term electricity load prediction remains uncertain. This study evaluates forecasting models ranging from classical regression techniques to advanced deep learning architectures using data from the ESD 2025 competition. The dataset includes two years of historical electricity load data, alongside temperature and global horizontal irradiance (GHI) across five sites, with a one-day-ahead forecasting horizon. Since actual test set load values remain undisclosed, leveraging predicted values would accumulate errors, making this a long-term forecasting challenge. We employ (i) Principal Component Analysis (PCA) for dimensionality reduction and (ii) frame the task as a regression problem, using temperature and GHI as covariates to predict load for each hour, (iii) ultimately stacking 24 models to generate yearly forecasts. Our results reveal that deep learning models, including TimeGPT, fail to consistently outperform simpler statistical and machine learning approaches due to the limited availability of training data and exogenous variables. In contrast, XGBoost, with minimal feature engineering, delivers the lowest error rates across all test cases while maintaining computational efficiency. This highlights the limitations of deep learning in long-term electricity forecasting and reinforces the importance of model selection based on dataset characteristics rather than complexity. Our study provides insights into practical forecasting applications and contributes to the ongoing discussion on the trade-offs between traditional and modern forecasting methods.
May 3, 2026 at 4:19 PM
r-bloggers.bsky.social
Down a Rabbit Hole with ARIMA Models

"In my previous post A First Look at TimeGPT using nixtlar, I used the auto.arima() function from the forecast package to fit an ARIMA model to a time series of electricity usage data in order to compare and ARIMA forecast with the TimeGPT foreca...

Cont..."
April 11, 2025 at 7:27 PM
r-bloggers.bsky.social
A First Look at TimeGPT using nixtlar

"This post is a first look at Nixtla’s TimeGPT generative, pre-trained transformer for time series forecasting using the nixtlar R package.
As described in Garza et al. (2021), TimeG..."

https://www.r-bloggers.com/2025/02/a-first-look-at-timegpt-using-nixtlar/
February 20, 2025 at 11:24 PM