Nixtla

?????Nixtla named as one of Fast Company’s Next Big Things in Tech ???? We're proud to share that we’ve been named to Fast Company's fourth annual Next Big Things in Tech list, honoring emerging technology that has a profound impact for industries—from education and sustainability to robotics and artificial intelligence. We are honored to be chosen alongside other game-changing organizations for the #FCTechAwards.?https://lnkd.in/e3t5h9Fa Time-series forecasting is a powerful method that leverages time-stamped data to predict future events and remove uncertainty from business conditions. Any organization that wants to perform forecasting or anomaly detection can benefit from a time series model, and we aim to do for time series what LLMs have done for language - making them accessible to anyone. Our nixtlaverse open source ecosystem has more than 18M downloads and is used by forecasters around the world. Our foundation model TimeGPT has made it easier for anyone to forecast using data they already have in Excel or other systems – such as sales, revenue and inventory data - without having to hire a team of engineers to develop custom models. With TimeGPT, we make time-series forecasting available to anyone with just three lines of code. “It’s a tremendous honor to have our time-series forecasting software recognized by Fast Company as groundbreaking technology that will have a profound impact on businesses,” says Max Mergenthaler Canseco Co-Founder and CEO of Nixtla. “Nixtla’s users come from big companies and small, government agencies, nonprofits and academic institutions, and they can create insights and use data to make decisions in ways that were not possible before. Our team has worked hard to bring this technology to market and make time-series forecasting available to everyone.” “The Next Big Things in Tech provides a fascinating glimpse at near- and long-term technological breakthroughs across a variety of sectors,” says Brendan Vaughan, editor-in-chief of Fast Company. “Spanning everything from semiconductors to agricultural gene editing, the companies featured in this year’s list are tackling some of the world’s most pressing and vexing problems.” ?? We’re grateful for this honor and the amazing community who does the work every day that continues to make forecasting the next big thing. ? Give forecasting a try or continue your time-series journey with our open source ecosystem and TimeGPT. https://lnkd.in/gvbF4QRW ?? Happy forecasting! #Forecasting #TimeSeries #MachineLearning #Python #DataScience

Thanks for the mention Zeel Thumar. We are curious to know what Clem Delangue ?? thinks about that statement.

Excited to share that my article "Can machine learning outperform Statistical models for Time Series Forecasting" published in Towards AI has been making waves on Medium , with about 15k reads and 1.1k claps! This shows the rising interest in ML models for time series forecasting and innovative libraries like Nixtla's MLforecast. If you're a data scientist looking to explore this field, you might want to check out the article and Nixtla's library! Link to the article: https://lnkd.in/gWssgniQ #MachineLearning #TimeSeriesForecasting #DataScience #Nixtla #MLforecast #ai #newintech

?? ?? New release of Hierarchical Forecast! ?? ?? HierachicalForecast?offers different reconciliation methods that render coherent forecasts across hierarchies. New release v0.4.3 adds the following features: ?? Sparse middle-out reconciliation via?MiddleOutSparse: Efficiently perform middle-out reconciliation in large-scale settings? ?? Support for exogenous variables in utils.aggregate: Aggregate exogenous covariates too when aggregating time series? ? Efficient Schafer-Strimmer for MinT: Perform MinT-shrink reconciliation blazingly fast? ?? Improves residuals-based reconciliation stability and faster ma.cov: Improved stability and NaN-handling, allowing more problems to be solvable with MinT-methods ?? Shout out to our community members?Christopher Titchen?and?Kurai Maingi?for their contributions! Note that as of v0.4.3, hierarchicalforecast no longer officially supports Python 3.8, which is EOL. Our priorities for the next month are (i) adding Polars support and (ii) adding temporal hierarchical reconciliation methods, but open to suggestions otherwise! ?Questions or suggestions for new features? Let us know as a comment or?file an issue on Github.? Get started with Hierarchical Forecast?: https://lnkd.in/gJVT4hBS ?? Happy forecasting! #Forecasting #TimeSeries #MachineLearning #Python #DataScience

?? ?? Presenting our R package for working with TimeGPT ?? ?? We’re excited to present?nixtlar v0.6.1, our R package for working with the?TimeGPT?API. As the R equivalent to?nixtla, the Python SDK for TimeGPT, nixtlar was already available on CRAN and has now been updated to?version 0.6.1. This new version incorporates the new TimeGPT API-v2 and extends support to tibbles. TimeGPT is the first foundation model for time series forecasting. With TimeGPT?you can quickly and easily generate accurate forecasts or conduct anomaly detection in just a few lines of code. nixtlar is designed to be user-friendly, allowing anyone within the R community to leverage generative AI for time series. Capabilities of nixtlar include: ?? Zero-shot inference:?Generate accurate forecasts with no prior model training. ?? Fine-tuning:?Enhance your predictions by fine-tuning the model to your specific dataset. ?? Uncertainty quantification:?Capture the full distribution of your predictions, either via quantile forecasts or prediction intervals. ?? R ecosystem integration:?Works with your favorite R data structures—data frames, tibbles, or tsibbles. nixtlar embodies Nixtla’s core philosophy to democratize access to state-of-the-art predictive insights, making advanced forecasting tools accessible to all. ?? Thank you for all the ideas and feedback from the R community that have contributed to nixtlar! ?? Links in the comments for getting started with nixtlar. And of course nixtlar already has its own hex sticker! Let us know in the comments if you'd like one! #Forecasting #TimeSeries #MachineLearning #AI #RStats #DataScience

? 5 ways companies can use time series forecasting Much of the data your company has is already time-stamped. It’s probably sitting in Excel spreadsheets, brimming with potential. Recent advances in AI, such as foundation models, make it possible for smaller companies to access time series forecasting to make predictions, reduce uncertainty, and gain business advantages. In this InfoWorld article Cristian Challu, Ph.D. shares five ways your business can use your data for time series forecasting. ?? * Turn Excel spreadsheets into future knowledge about your business. * Use information about external factors to make predictions. * Measure uncertainty with probabilistic forecasts. * Evaluate different future scenarios. * Detect anomalies that will affect your predictions or identify unusual patterns. https://lnkd.in/gQkpucPy #timeseries #forecasting #machinelearning #ai #python

?? Love all the great resources on time series forecasting. Congratulations on the new edition Manu Joseph & Jeffrey Tackes!

?? ?? Getting Started with Transformer Forecasting on Databricks ?? ?? If you're a manager, analyst or data scientist using Databricks as the basis for your forecasting efforts, Ryuta Yoshimatsu, Puneet Jain and Bryan Smith share a high-level introduction to generative AI forecasting models and a series of notebooks that demonstrate how organizations housing their data in Databricks can easily tap into several of the most popular forecasting models. Post: https://lnkd.in/gHxQdZA8 Notebooks: https://lnkd.in/gH9Jc3-9 The notebooks on TimeGPT are a great way to get started with TimeGPT and Databricks. You can freely download these notebooks and employ them within your Databricks environment to gain familiarity with their use or adapt them for your needs. ?? Thanks Ryuta, Puneet and Bryan for the post!

As a time series enthusiast, I couldn’t resist giving Nicolas Vandeput's competition a shot (although I hadn’t planned on participating due to my personal holiday plans). After trying a few statistical models, I took my laptop to a coffee shop this morning and decided to try some tree-based models. Two coffees later, I built a model that now has me in 9th place (around the top 5% of all participants). Huge shout-out to Nixtla for building an amazing library that made it easy to experiment with different models, feature engineering techniques and quickly evaluate performance. If you're into time series forecasting, I highly recommend checking it out—it's a game changer! Most likely, I won’t have time to participate further, but I wish the best of luck to all participants. I can't wait to dive deeper into the solutions once the competition wraps up, and I'm looking forward to sharing my notebook soon. #TimeSeries #DataScience #MachineLearning #Forecasting #Nixtla #AI #FeatureEngineering

? ?? Forecasting stock trade data using TimescaleDB??? ? In Azul Garza most recent live stream, she showed how to forecast stock trade data using Timescale's TimescaleDB. In the videos she shows how to: ? create a TimescaleDB database ?? ingest data to the database ?? use TimeGPT to generate forecasts on stock trade data The forecasting is just two lines of code, and the reading from the TimescaleDB database and writing the forecasts back is just two more. Check out the videos and the github repo with the code from this project! https://bit.ly/4gU7OiH This Friday Azul Garza is forecasting real-time stock trade data (using, of course, foundation time series models). ?? More streaming to come! ? What use case with TimeGPT would you like to see in a live stream?