Excess Returns  cover image

Applying Machine Learning to Value Investing with Euclidean’s John Alberg

Excess Returns

00:00

How Much Data Is Available for Machine Learning?

There are 5,000 stocks available at any point in time for machine learning to work on. This is far too small for most machine learning applications and impossibly small for advanced approaches such as deep learning. For me, when I think about that, there's more than 3 million examples of companies with different outcomes which can be applied to new companies. There's not as much data as there is if you were trying to build a language model where you have all the Wikipedia and every book ever read but still certainly enough data.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app