All videos
0:00 / 0:00
ai

Time series Forecasting using GPT models | Max Mergenthaler Canseco

Jay Shah17 June 2026Watch on YouTube

Description

Max is the CEO and co-founder of Nixtla, where he is developing highly accurate forecasting models using time series data and deep learning techniques, which developers can use to build their own pipelines. Max is a self-taught programmer and researcher with a lot of prior experience building things from scratch. 00:00:50 Introduction 00:01:26 Entry point in AI 00:04:25 Origins of Nixtla 00:07:30 Idea to product 00:11:21 Behavioral economics & psychology to time series prediction 00:16:00 Landscape of time series prediction 00:26:10 Foundation models in time series 00:29:15 Building TimeGPT 00:31:36 Numbers and GPT models 00:34:35 Generalization to real world datasets 00:38:10 Math reasoning with LLMs 00:40:48 Neural Hierarchical Interpolation for Time Series Forecasting 00:47:15 TimeGPT applications 00:52:20 Pros and Cons of open-source in AI 00:57:20 Insights from building AI products 01:02:15 Tips to researchers & hype vs reality of AI More about Max: https://www.linkedin.com/in/mergenthaler/ and Nixtla: https://www.nixtla.io/ Check out TimeGPT: https://github.com/Nixtla/nixtla About the Host: Jay is a PhD student at Arizona State University working on improving AI for medical diagnosis and prognosis. Linkedin: https://www.linkedin.com/in/shahjay22/ Twitter: https://twitter.com/jaygshah22 Homepage: https://www.public.asu.edu/~jgshah1/ for any queries. Stay tuned for upcoming webinars! ***Disclaimer: The information in this video represents the views and opinions of the speaker and does not necessarily represent the views or opinions of any institution. It does not constitute an endorsement by any Institution or its affiliates of such video content.***

What you'll learn

  • TimeGPT is a foundation model using deep learning for accurate time series forecasting that developers can integrate into their own pipelines.
  • Foundation models in time series can better generalize to real-world datasets through training on large volumes of diverse time series data.
  • TimeGPT's architecture combines insights from behavioral economics, psychology, and Neural Hierarchical Interpolation for improved forecasts.
  • Building AI products requires balancing open-source transparency with commercial viability while addressing practical applications across industries.

Frequently asked questions

What is TimeGPT and how does it differ from traditional forecasting methods?
TimeGPT is a foundation model applying deep learning and GPT architectures to time series forecasting. Unlike traditional methods that often require retraining per use case, TimeGPT can learn to generalize from large datasets and adapt to diverse real-world applications.
How does Nixtla's approach with behavioral economics contribute to better time series prediction?
Nixtla integrates insights from behavioral economics and psychology into model design to better predict patterns in human behavior. This is particularly useful for datasets where human decisions or economic factors influence the time series.
What are the practical applications of TimeGPT for businesses and developers?
Developers can use TimeGPT in their own forecasting pipelines for diverse applications across industries where accurate predictions of future values are critical. This ranges from supply chain to financial forecasting.
What advantages and disadvantages does Max see in open-source AI development?
Open-source offers transparency and community contributions, but brings challenges around commercialization and maintenance. Max emphasizes that balancing these is crucial when building AI products that must be both innovative and sustainable.

Topics

time series forecastingfoundation modelsgpt modelsdeep learningnixtla