Richie CottonSenior Data Evangelist, DataCamp · Ask me about data and AI upskilling

Do You Actually Need a Foundation Model? #AI

Name: Do You Actually Need a Foundation Model? #AI
Uploaded: 2026-04-22T14:01:04+00:00
Duration: 31 s
Channel: Richie Cotton
Description: In this segment, the speaker outlines key considerations for selecting forecasting models. He emphasizes the importance of benchmarking models rather…

22 Apr 2026 · 1 min

Watch on YouTube

0:31

In this segment, the speaker outlines key considerations for selecting forecasting models. He emphasizes the importance of benchmarking models rather than assuming a foundation model is required. The advice is to experiment with various model types, assess their performance on your specific data, and conduct “horse racing” comparisons using backtesting to determine the most effective approach.

Chapters

There are a couple of things that you need to consider when you are choosing a model. One is the— you want to benchmark it. It's not always you need a foundation model to do a forecast. You need to experiment and understand which type of models will work on your data. You can use different— and that's what I love to do generally when I'm doing forecasting, not necessarily foundation models, but traditional forecasting. I like to run horse racing between different models using backtesting.