logoalt Hacker News

beernet • today at 11:50 AM • 3 replies • view on HN

Meh....time series data is fundamentally different from textual data. I see why a time series "foundation model" seems appealing, especially to the marketing folks at Mistral. Real-world usability is very limited, which is probably the reason why the blog post features an imaginary customer rather than an actual reference.


Replies

AtHeartEngineer • today at 12:12 PM

Time based data is extremely important, and there are tons of techniques out there to train super fast super small models, but they are a pain in the ass to tune. I could see a foundation model that is kind of good at a lot of things, that could be fine tuned or used when you want something more straight forward to use to analyze a bunch of data.

Honestly this might be very good for feature selection to refine a much more specialized model.

saithound • today at 11:52 AM

Agered. These are essentially numerology models.

GeoffNN • today at 11:53 AM

Cofounder of The Forecasting Company here - disagree on this. The models now work quite well and are in prod at a number of places, including very sophisticated places - quant funds, top retail cos etc

➕ show 2 replies