Overview
Watch a 43-minute AutoML Seminar presentation exploring how pretrained models can revolutionize time series forecasting across energy, retail, and financial sectors. Learn from speaker Oleksandr Shchur about Chronos, a groundbreaking family of pretrained forecasting models adapted from Large Language Model architectures. Discover how these models achieve impressive zero-shot performance on new datasets, potentially streamlining forecasting workflows. Gain insights into the challenges and opportunities in developing pretrained models for time series forecasting, and understand the potential role of AutoML methods in advancing this technology.
Syllabus
Chronos: Time series forecasting in the age of pretrained models
Taught by
AutoML Seminars