Loading…
Data Tech 2026 has ended

Friday May 15, 2026 11:45am - 12:15pm CDT
This talk builds on prior work presented at FASTCon 2026.

Time Series Foundation Models (TSFMs) are gaining traction in forecasting, but their real-world behavior is more nuanced than the hype suggests. In our experiments, we observe that performance varies across data regimes, forecast horizons, and retraining setups—with only small differences among top models.

This talk focuses on the why behind these results.

We connect architectural choices in models like Chronos/Chronos2, TimeGPT, and TiReX to their observed behavior—covering data efficiency, generalization, regime sensitivity, and stability.

Rather than asking “which model is best,” we provide a practical framework for understanding when and why each model works, helping practitioners make more informed, context-driven decisions.
Speakers
avatar for Sruthi Pisipati, MS

Sruthi Pisipati, MS

Principal Data Scientist, Boston Scientific Corporation
Sruthi Pisipati, Principal Data Scientist at Boston Scientific, leverages AI to drive innovation in medical device technology. Her interest areas include Vision, Gen AI and Forecasting domains.
Friday May 15, 2026 11:45am - 12:15pm CDT
(h) Proverb / Edison Best Buy HQ, 7700 Knox Ave S, Richfield, MN 55423

Log in to save this to your schedule, view media, leave feedback and see who's attending!

Share Modal

Share this link via

Or copy link