Time Series Forecasting with Marco Peixeiro

If you're eager to join future webinars, unlock a vast library of quantitative finance resources and educational content, and become part of a vibrant community of like-minded individuals, you'll find all that and more at https://community.quantopian.com/home. In this episode of Quantopian Book Conversation, Professor Esfandiar Haghverdi sit down with applied AI scientist and author Marco Peixeiro to explore the evolving world of time series forecasting—from traditional statistical models to cutting-edge foundation models like TimeGPT. Marco discusses his two books: 📘 Time Series Forecasting in Python 📗 Time Series Forecasting Using Foundation Models We dive into how the field has shifted from classical approaches like ARIMA to modern deep learning systems, and why foundation models are becoming the new baseline for forecasting. Marco shares insights from his work on TimeGPT, explains how zero-shot forecasting works in practice, and reflects on the challenges of applying these models to real-world data—especially in areas like finance where noise, regime changes, and unpredictability are constant. The conversation also touches on interpretability, the limits of predictive accuracy in trading, and what’s coming next—from causal AI to models that combine numerical and textual data. Topics covered include: From statistical models to foundation models in forecasting Zero-shot predictions and TimeGPT Challenges with real-world time series data Explainability in deep learning models The future of forecasting and AI About the Author: Marco Peixeiro is an Applied AI Scientist at Nixtla, where he develops NLP solutions to automate customer service. He is also a technical blogger for Towards Data Science on Medium, a course creator on Udemy, and the author of Time Series Forecasting in Python and Time Series Forecasting Using Foundation Models. He previously worked as a senior data scientist at one of Canada’s largest banks. Resources: Marco's Website: https://www.datasciencewithmarco.com/... Time Series Forecasting in Python: https://www.manning.com/books/time-se... Time Series Forecasting Using Foundation Models: https://www.manning.com/books/time-se... Learn more by subscribing to our YouTube channel to access all of our videos. As always, if there are any topics you would like us to focus on for future videos, please comment below or send us a quick note at [email protected]. Disclaimer Quantopian provides this presentation to help people write trading algorithms - it is not intended to provide investment advice. More specifically, the material is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory or other services by Quantopian. In addition, the content neither constitutes investment advice nor offers any opinion with respect to the suitability of any security or any specific investment. Quantopian makes no guarantees as to accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances.